diff --git a/ar/overview/getting-started.mdx b/ar/overview/getting-started.mdx
index af44191..5a6cfcc 100644
--- a/ar/overview/getting-started.mdx
+++ b/ar/overview/getting-started.mdx
@@ -1,335 +1,340 @@
---
-title: البدء
-description: "بدء سريع لـ Venice API — أنشئ مفتاح API، أرسل أول chat completion، واستكشف endpoints الصور والفيديو والصوت في دقائق."
-"og:title": "البدء السريع | وثائق Venice API"
+title: "البدء السريع"
+description: "دليل البدء السريع لواجهة Venice API — أنشئ مفتاح API، وأرسل أول طلب إكمال محادثة، واستكشف نقاط النهاية الخاصة بالصور والفيديو والصوت في دقائق."
+og:title: "البدء السريع | وثائق Venice API"
---
-ابدأ مع Venice API في دقائق. ولِّد مفتاح API، ونفّذ طلبك الأول، وابدأ البناء.
+ابدأ باستخدام Venice API في دقائق. أنشئ مفتاح API، وقم بإجراء أول طلب لك، وابدأ في البناء.
## البدء السريع
- اذهب إلى [إعدادات Venice API](https://venice.ai/settings/api) وأنشئ مفتاح API جديدًا.
+ توجه إلى [إعدادات Venice API](https://venice.ai/settings/api) وقم بإنشاء مفتاح API جديد.
- للحصول على إرشادات تفصيلية، راجع [دليل مفتاح API](/guides/getting-started/generating-api-key).
+ للحصول على شرح تفصيلي، راجع [دليل مفتاح API](/guides/getting-started/generating-api-key).
-
-
- أضف مفتاح API إلى بيئتك. يمكنك تصديره في الصدفة:
+
+ أضف مفتاح API إلى بيئتك. يمكنك تصديره في الطرفية (shell):
```bash
export VENICE_API_KEY='your-api-key-here'
```
- أو إضافته إلى ملف `.env` في مشروعك:
+ أو أضفه إلى ملف `.env` في مشروعك:
```bash
VENICE_API_KEY=your-api-key-here
```
-
-
- Venice متوافق مع OpenAI، لذا يمكنك استخدام OpenAI SDK. إن فضّلت استخدام cURL أو طلبات HTTP خام، يمكنك تخطّي هذه الخطوة.
+
+ Venice متوافقة مع OpenAI، لذا يمكنك استخدام OpenAI SDK. إذا كنت تفضل استخدام cURL أو طلبات HTTP الأولية، فيمكنك تخطي هذه الخطوة.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
-
+
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
**أدوار الرسائل:**
- - `system` - تعليمات لكيفية تصرّف النموذج
- - `user` - تعليماتك أو أسئلتك
- - `assistant` - استجابات النموذج السابقة (لمحادثات متعددة الأدوار)
+
+ - `system` - تعليمات حول كيفية تصرف النموذج
+ - `user` - مطالباتك أو أسئلتك
+ - `assistant` - ردود النموذج السابقة (للمحادثات متعددة الأدوار)
- `tool` - نتائج استدعاء الدوال (عند استخدام الأدوات)
+
+ يتضمن كل طلب معرّف `model`. لاستخدام نموذج مختلف، غيّر قيمة `model` في طلبك. الخيارات الشائعة:
-
- يتضمن كل طلب معرّف `model`. لاستخدام نموذج مختلف، غيّر قيمة `model` في طلبك. خيارات شائعة:
- `zai-org-glm-5` - النموذج الافتراضي لمعظم حالات الاستخدام
- - `kimi-k2-6` - تفكير قوي للمهام الأكثر تعقيدًا
+ - `kimi-k2-6` - استدلال قوي للمهام الأكثر تعقيدًا
- `claude-opus-4-8` - نموذج عالي الذكاء للمهام المعقدة
- - `venice-uncensored-1-2` - النموذج غير المُقيَّد من Venice
+ - `venice-uncensored-1-2` - نموذج Venice غير الخاضع للرقابة
-
- تصفّح القائمة الكاملة للنماذج مع التسعير والقدرات وحدود السياق
+
+ تصفح القائمة الكاملة للنماذج مع الأسعار والقدرات وحدود السياق
-
-
- يمكنك تفعيل ميزات خاصة بـ Venice مثل البحث في الويب باستخدام `venice_parameters`:
+
+ يمكنك اختيار تمكين الميزات الخاصة بـ Venice مثل البحث على الويب باستخدام `venice_parameters`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
- راجع كل [المعاملات المتاحة](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
+ راجع جميع [المعاملات المتاحة](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
-
- بثّ الاستجابات في الوقت الفعلي باستخدام `stream=True`:
+
+ قم ببث الردود في الوقت الفعلي باستخدام `stream=True`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
-
- تحكّم بكيفية استجابة النموذج بمعاملات مثل temperature و max tokens والمزيد:
+
+ تحكم في كيفية استجابة النموذج باستخدام معاملات مثل temperature و max tokens وغيرها:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
+ }
+ }'
+ ```
+
راجع [وثائق Chat Completions](/api-reference/endpoint/chat/completions) لمزيد من المعلومات حول جميع المعاملات المدعومة.
@@ -338,669 +343,55 @@ description: "بدء سريع لـ Venice API — أنشئ مفتاح API، أر
---
-## قدرات إضافية
-
-### توليد الصور
-
-أنشئ صورًا من تعليمات نصية باستخدام نماذج الانتشار:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**ملاحظة:** تُرجع الاستجابة صورًا مُرمَّزة بـ base64 في مصفوفة `images`. فكّ ترميز سلسلة base64 لحفظ الصورة أو عرضها.
-
-**نماذج صور شائعة:**
-- `qwen-image` - أعلى جودة لتوليد الصور
-- `venice-sd35` - الخيار الافتراضي، يعمل مع جميع الميزات
-- `hidream` - توليد سريع للاستخدام الإنتاجي
-
-
- راجع كل نماذج الصور المتاحة مع التسعير والقدرات
-
-
-لخيارات معاملات أكثر تقدمًا مثل `cfg_scale` و `negative_prompt` و `style_preset` و `seed` و `variants` وغيرها، راجع [مرجع Images API](/api-reference/endpoint/image/generate).
-
-### تحرير الصور
-
-عدّل الصور الموجودة بـ inpainting مدفوع بالذكاء الاصطناعي باستخدام نموذج Qwen-Image:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**ملاحظة:** يستخدم محرّر الصور نموذج Qwen-Image وهو نقطة نهاية تجريبية. أرسل صورة الإدخال كسلسلة مُرمَّزة بـ base64، وتُرجع الواجهة الصورة المعدّلة كبيانات ثنائية.
-
-راجع [Image Edit API](/api-reference/endpoint/image/edit) لجميع المعاملات.
-
-### ترقية دقّة الصور
-
-حسّن الصور إلى دقّات أعلى:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**ملاحظة:** أرسل صورة الإدخال كسلسلة مُرمَّزة بـ base64، وتُرجع الواجهة الصورة المُرقّاة كبيانات ثنائية.
-
-راجع [Image Upscale API](/api-reference/endpoint/image/upscale) لجميع المعاملات.
-
-### من نص إلى كلام
-
-حوّل النص إلى صوت مع أكثر من 50 صوتًا متعدد اللغات:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-يدعم نموذج `tts-kokoro` أكثر من 50 صوتًا متعدد اللغات بما في ذلك `af_sky` و`af_nova` و`am_liam` و`bf_emma` و`zf_xiaobei` و`jm_kumo`.
-
-راجع [TTS API](/api-reference/endpoint/audio/speech) لجميع خيارات الأصوات.
-
-### من كلام إلى نص
-
-فرّغ ملفات الصوت إلى نص:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-الصيغ المدعومة: WAV، FLAC، MP3، M4A، AAC، MP4. فعّل `timestamps=true` للحصول على بيانات توقيت على مستوى الكلمة.
-
-راجع [Transcriptions API](/api-reference/endpoint/audio/transcriptions) لجميع الخيارات.
-
-### التضمينات (Embeddings)
-
-ولّد تضمينات متجهية للبحث الدلالي و RAG والتوصيات:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-راجع [Embeddings API](/api-reference/endpoint/embeddings/generate) للمعالجة على دفعات والخيارات المتقدمة.
-
-### الرؤية (متعدد الوسائط)
-
-حلّل الصور بجانب النص باستخدام نماذج قادرة على الرؤية مثل `qwen3-vl-235b-a22b`:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
- }
- ]
- }
- ]
- }'
- ```
-
-
-### استدعاء الدوال (Function Calling)
-
-عرّف دوالًا يمكن للنماذج استدعاؤها للتفاعل مع أدوات وواجهات خارجية:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
- }
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
- }'
- ```
-
-
----
-
## الخطوات التالية
-بعد أن قمت بطلباتك الأولى، استكشف المزيد مما يقدّمه Venice API:
+الآن بعد أن أجريت طلباتك الأولى، استكشف المزيد مما تقدمه Venice API:
-
- قارن جميع النماذج المتاحة مع قدراتها وتسعيرها وحدود السياق
+
+ قارن بين جميع النماذج المتاحة مع قدراتها وأسعارها وحدود السياق
-
- استكشف وثائق API التفصيلية مع كل نقاط النهاية والمعاملات
+
+
+ استكشف وثائق API التفصيلية مع جميع نقاط النهاية والمعاملات
-
- تعلّم كيف تحصل على استجابات JSON بمخططات مضمونة
+
+
+ تعلم كيفية الحصول على استجابات JSON بمخططات مضمونة
+
- ابنِ تطبيقات وكلاء، ووكلاء برمجة، وأدوات MCP، ومهارات، وتدفقات عمل تشفيرية
+ قم بالبناء باستخدام تطبيقات الوكلاء ووكلاء البرمجة وأدوات MCP والمهارات وسير عمل العملات المشفرة
### موارد إضافية
-
- افهم حدود المعدّل وأفضل الممارسات للاستخدام الإنتاجي
+
+ افهم حدود المعدل وأفضل الممارسات للاستخدام في بيئة الإنتاج
+
- مرجع للتعامل مع أخطاء API واستكشاف المشكلات
+ مرجع للتعامل مع أخطاء الـ API واستكشاف المشكلات وإصلاحها
+
- استورد مجموعة Postman الكاملة لاختبار سهل
+ استورد مجموعة Postman الكاملة الخاصة بنا للاختبار السهل
+
- تعرّف على بنية Venice التي تضع الخصوصية أولًا وتعامل البيانات
+ تعرف على بنية Venice التي تعطي الأولوية للخصوصية وطريقة التعامل مع البيانات
---
-## بحاجة إلى مساعدة؟
+## هل تحتاج إلى مساعدة؟
-- **مجتمع Discord**: انضم إلى [خادم Discord الخاص بنا](https://discord.gg/askvenice) للدعم والنقاشات
-- **الوثائق**: تصفّح [مرجع API الكامل](/api-reference/api-spec)
-- **صفحة الحالة**: تحقّق من حالة الخدمة على [veniceai-status.com](https://veniceai-status.com)
-- **Twitter**: تابع [@AskVenice](https://x.com/AskVenice) للتحديثات
+- **مجتمع Discord**: انضم إلى [خادم Discord](https://discord.gg/askvenice) الخاص بنا للحصول على الدعم والمناقشات
+- **الوثائق**: تصفح [مرجع الـ API الكامل](/api-reference/api-spec)
+- **صفحة الحالة**: تحقق من حالة الخدمة في [veniceai-status.com](https://veniceai-status.com)
+- **تويتر**: تابع [@AskVenice](https://x.com/AskVenice) للحصول على التحديثات
diff --git a/de/overview/getting-started.mdx b/de/overview/getting-started.mdx
index 9fe202b..1819844 100644
--- a/de/overview/getting-started.mdx
+++ b/de/overview/getting-started.mdx
@@ -1,1006 +1,397 @@
---
-title: Erste Schritte
-description: "Schnellstart für die Venice API — API-Schlüssel generieren, erste Chat-Completion senden und Bild-, Video- und Audio-Endpunkte in Minuten erkunden."
-"og:title": "Quickstart | Venice API Docs"
+title: "Schnellstart"
+description: "Schnellstart für die Venice-API — erstelle einen API-Key, sende deine erste Chat-Completion und erkunde Bild-, Video- und Audio-Endpunkte in wenigen Minuten."
+og:title: "Schnellstart | Venice-API-Dokumentation"
---
-In wenigen Minuten mit der Venice API einsatzbereit. Generieren Sie einen API-Schlüssel, stellen Sie Ihre erste Anfrage und starten Sie mit dem Bauen.
+Werde mit der Venice-API in wenigen Minuten startklar. Erstelle einen API-Key, sende deine erste Anfrage und beginne zu entwickeln.
-## Quickstart
+## Schnellstart
-
- Gehen Sie zu Ihren [Venice-API-Einstellungen](https://venice.ai/settings/api) und generieren Sie einen neuen API-Schlüssel.
+
+ Gehe zu deinen [Venice-API-Einstellungen](https://venice.ai/settings/api) und erstelle einen neuen API-Key.
- Für eine ausführliche Anleitung siehe den [API-Schlüssel-Leitfaden](/guides/getting-started/generating-api-key).
+ Eine ausführliche Anleitung findest du im [API-Key-Leitfaden](/guides/getting-started/generating-api-key).
-
-
- Fügen Sie Ihren API-Schlüssel Ihrer Umgebung hinzu. Sie können ihn in Ihrer Shell exportieren:
+
+ Füge deinen API-Key zu deiner Umgebung hinzu. Du kannst ihn in deiner Shell exportieren:
```bash
export VENICE_API_KEY='your-api-key-here'
```
- Oder fügen Sie ihn zu einer `.env`-Datei in Ihrem Projekt hinzu:
+ Oder füge ihn zu einer `.env`-Datei in deinem Projekt hinzu:
```bash
VENICE_API_KEY=your-api-key-here
```
-
-
- Venice ist OpenAI-kompatibel, sodass Sie das OpenAI-SDK verwenden können. Wenn Sie lieber cURL oder rohe HTTP-Anfragen verwenden, können Sie diesen Schritt überspringen.
+
+ Venice ist OpenAI-kompatibel, sodass du das OpenAI-SDK verwenden kannst. Wenn du lieber cURL oder rohe HTTP-Anfragen verwendest, kannst du diesen Schritt überspringen.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
-
+
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
**Nachrichtenrollen:**
- - `system` - Anweisungen für das Verhalten des Modells
- - `user` - Ihre Prompts oder Fragen
- - `assistant` - Frühere Modellantworten (für mehrstufige Konversationen)
- - `tool` - Function-Calling-Ergebnisse (bei Verwendung von Tools)
+
+ - `system` - Anweisungen dazu, wie sich das Modell verhalten soll
+ - `user` - Deine Prompts oder Fragen
+ - `assistant` - Vorherige Modellantworten (für mehrstufige Konversationen)
+ - `tool` - Ergebnisse von Function Calls (bei Verwendung von Tools)
+
+ Jede Anfrage enthält eine `model`-ID. Um ein anderes Modell zu verwenden, ändere den `model`-Wert in deiner Anfrage. Beliebte Auswahlmöglichkeiten:
-
- Jede Anfrage enthält eine `model`-ID. Um ein anderes Modell zu verwenden, ändern Sie den Wert `model` in Ihrer Anfrage. Beliebte Optionen:
- - `zai-org-glm-5` - Standardmodell für die meisten Use Cases
+ - `zai-org-glm-5` - Standardmodell für die meisten Anwendungsfälle
- `kimi-k2-6` - Starkes Reasoning für komplexere Aufgaben
- - `claude-opus-4-8` - High-Intelligence-Modell für komplexe Aufgaben
- - `venice-uncensored-1-2` - Venice's unzensiertes Modell
+ - `claude-opus-4-8` - Hochintelligentes Modell für komplexe Aufgaben
+ - `venice-uncensored-1-2` - Venices unzensiertes Modell
- Durchsuchen Sie die vollständige Liste der Modelle mit Preisen, Capabilities und Kontextlimits
+ Durchsuche die vollständige Liste der Modelle mit Preisen, Fähigkeiten und Kontextgrenzen
-
-
- Sie können Venice-spezifische Funktionen wie Web Search über `venice_parameters` aktivieren:
+
+ Du kannst Venice-spezifische Funktionen wie die Websuche über `venice_parameters` aktivieren:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
Siehe alle [verfügbaren Parameter](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
- Streamen Sie Antworten in Echtzeit mit `stream=True`:
+ Streame Antworten in Echtzeit mit `stream=True`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
- Steuern Sie das Antwortverhalten des Modells mit Parametern wie temperature, max tokens und mehr:
+ Steuere, wie das Modell antwortet, mit Parametern wie Temperature, Max Tokens und mehr:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
-
- Weitere Informationen zu allen unterstützten Parametern finden Sie in der [Chat-Completions-Dokumentation](/api-reference/endpoint/chat/completions).
-
-
-
----
-
-## Weitere Funktionen
-
-### Bildgenerierung
-
-Erstellen Sie Bilder aus Text-Prompts mit Diffusion-Modellen:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**Hinweis:** Die Antwort enthält base64-kodierte Bilder im `images`-Array. Dekodieren Sie den base64-String, um das Bild zu speichern oder anzuzeigen.
-
-**Beliebte Bildmodelle:**
-- `qwen-image` - Höchste Qualität bei der Bildgenerierung
-- `venice-sd35` - Standardwahl, funktioniert mit allen Funktionen
-- `hidream` - Schnelle Generierung für den Produktiveinsatz
-
-
- Sehen Sie alle verfügbaren Bildmodelle mit Preisen und Capabilities
-
-
-Für erweiterte Parameter-Optionen wie `cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` und mehr siehe die [Images-API-Referenz](/api-reference/endpoint/image/generate).
-
-### Bildbearbeitung
-
-Modifizieren Sie vorhandene Bilder mit KI-gestütztem Inpainting unter Verwendung des Qwen-Image-Modells:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**Hinweis:** Der Image-Editor verwendet das Qwen-Image-Modell und ist ein experimenteller Endpoint. Senden Sie das Eingabebild als base64-kodierten String, und die API gibt das bearbeitete Bild als Binärdaten zurück.
-
-Alle Parameter siehe die [Image-Edit-API](/api-reference/endpoint/image/edit).
-
-### Bild-Upscaling
-
-Verbessern und skalieren Sie Bilder auf höhere Auflösungen:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**Hinweis:** Senden Sie das Eingabebild als base64-kodierten String, und die API gibt das hochskalierte Bild als Binärdaten zurück.
-
-Alle Parameter siehe die [Image-Upscale-API](/api-reference/endpoint/image/upscale).
-
-### Text-to-Speech
-
-Wandeln Sie Text in Audio mit mehr als 50 mehrsprachigen Stimmen um:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-Das `tts-kokoro`-Modell unterstützt mehr als 50 mehrsprachige Stimmen, einschließlich `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` und `jm_kumo`.
-
-Alle Stimm-Optionen siehe die [TTS-API](/api-reference/endpoint/audio/speech).
-
-### Speech-to-Text
-
-Transkribieren Sie Audiodateien zu Text:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-Unterstützte Formate: WAV, FLAC, MP3, M4A, AAC, MP4. Aktivieren Sie `timestamps=true`, um Timing-Daten auf Wort-Ebene zu erhalten.
-
-Alle Optionen siehe die [Transcriptions-API](/api-reference/endpoint/audio/transcriptions).
-
-### Embeddings
-
-Generieren Sie Vektor-Embeddings für semantische Suche, RAG und Empfehlungen:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-Batch-Verarbeitung und erweiterte Optionen siehe die [Embeddings-API](/api-reference/endpoint/embeddings/generate).
-
-### Vision (Multimodal)
-
-Analysieren Sie Bilder gemeinsam mit Text mit vision-fähigen Modellen wie `qwen3-vl-235b-a22b`:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### Function Calling
-
-Definieren Sie Funktionen, die Modelle aufrufen können, um mit externen Tools und APIs zu interagieren:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ Weitere Informationen zu allen unterstützten Parametern findest du in der [Chat-Completions-Dokumentation](/api-reference/endpoint/chat/completions).
+
+
---
## Nächste Schritte
-Jetzt, da Sie Ihre ersten Anfragen gestellt haben, entdecken Sie mehr von dem, was die Venice API zu bieten hat:
+Jetzt, wo du deine ersten Anfragen gesendet hast, erkunde mehr von dem, was die Venice-API zu bieten hat:
- Vergleichen Sie alle verfügbaren Modelle mit ihren Capabilities, Preisen und Kontextlimits
+ Vergleiche alle verfügbaren Modelle mit ihren Fähigkeiten, Preisen und Kontextgrenzen
+
- Erkunden Sie die detaillierte API-Dokumentation mit allen Endpoints und Parametern
+ Erkunde die detaillierte API-Dokumentation mit allen Endpunkten und Parametern
+
- Erfahren Sie, wie Sie JSON-Antworten mit garantierten Schemas erhalten
+ Erfahre, wie du JSON-Antworten mit garantierten Schemata erhältst
-
- Bauen Sie mit Agent-Apps, Coding-Agenten, MCP-Tools, Skills und Krypto-Workflows
+
+
+ Entwickle mit Agent-Apps, Coding-Agenten, MCP-Tools, Skills und Krypto-Workflows
-### Zusätzliche Ressourcen
+### Weitere Ressourcen
- Verstehen Sie Rate-Limits und Best Practices für den Produktiveinsatz
+ Verstehe Rate Limits und Best Practices für den produktiven Einsatz
+
- Referenz für den Umgang mit API-Fehlern und Troubleshooting
+ Referenz zum Umgang mit API-Fehlern und zur Fehlerbehebung
-
- Importieren Sie unsere vollständige Postman-Collection zum einfachen Testen
+
+
+ Importiere unsere vollständige Postman-Sammlung für einfaches Testen
+
- Erfahren Sie mehr über die datenschutzorientierte Architektur und Datenverarbeitung von Venice
+ Erfahre mehr über Venices datenschutzorientierte Architektur und den Umgang mit Daten
---
-## Brauchen Sie Hilfe?
+## Brauchst du Hilfe?
-- **Discord-Community**: Treten Sie unserem [Discord-Server](https://discord.gg/askvenice) für Support und Diskussionen bei
-- **Dokumentation**: Durchsuchen Sie unsere [vollständige API-Referenz](/api-reference/api-spec)
-- **Status-Seite**: Prüfen Sie den Dienststatus auf [veniceai-status.com](https://veniceai-status.com)
-- **Twitter**: Folgen Sie [@AskVenice](https://x.com/AskVenice) für Updates
+- **Discord-Community**: Tritt unserem [Discord-Server](https://discord.gg/askvenice) für Support und Diskussionen bei
+- **Dokumentation**: Durchsuche unsere [vollständige API-Referenz](/api-reference/api-spec)
+- **Statusseite**: Prüfe den Servicestatus unter [veniceai-status.com](https://veniceai-status.com)
+- **Twitter**: Folge [@AskVenice](https://x.com/AskVenice) für Updates
diff --git a/es/overview/getting-started.mdx b/es/overview/getting-started.mdx
index 43f3874..5922687 100644
--- a/es/overview/getting-started.mdx
+++ b/es/overview/getting-started.mdx
@@ -1,113 +1,115 @@
---
-title: Empezar
-description: "Quickstart de la API de Venice — genera una clave de API, envía tu primera chat completion y explora los endpoints de imagen, vídeo y audio en minutos."
-"og:title": "Quickstart | Venice API Docs"
+title: "Inicio rápido"
+description: "Inicio rápido para la API de Venice: genera una clave de API, envía tu primera completación de chat y explora los endpoints de imagen, video y audio en minutos."
+og:title: "Inicio rápido | Documentación de la API de Venice"
---
-Empieza a usar la API de Venice en minutos. Genera una API key, haz tu primera solicitud y empieza a construir.
+Empieza a usar la API de Venice en minutos. Genera una clave de API, realiza tu primera solicitud y comienza a construir.
## Inicio rápido
-
- Ve a tu [configuración de la API de Venice](https://venice.ai/settings/api) y genera una nueva API key.
+
+ Ve a la [configuración de la API de Venice](https://venice.ai/settings/api) y genera una nueva clave de API.
- Para un recorrido detallado, consulta la [guía de API Key](/guides/getting-started/generating-api-key).
+ Para un recorrido detallado, consulta la [guía de claves de API](/guides/getting-started/generating-api-key).
-
-
- Añade tu API key a tu entorno. Puedes exportarla en tu shell:
+
+ Añade tu clave de API a tu entorno. Puedes exportarla en tu shell:
```bash
export VENICE_API_KEY='your-api-key-here'
```
- O añadirla a un archivo `.env` en tu proyecto:
+ O añádela a un archivo `.env` en tu proyecto:
```bash
VENICE_API_KEY=your-api-key-here
```
-
- Venice es compatible con OpenAI, por lo que puedes usar el SDK de OpenAI. Si prefieres usar cURL o solicitudes HTTP en bruto, puedes saltarte este paso.
+ Venice es compatible con OpenAI, así que puedes usar el SDK de OpenAI. Si prefieres usar cURL o solicitudes HTTP directas, puedes omitir este paso.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
- **Roles de mensaje:**
- - `system` - Instrucciones para el comportamiento del modelo
+ **Roles de los mensajes:**
+
+ - `system` - Instrucciones sobre cómo debe comportarse el modelo
- `user` - Tus prompts o preguntas
- - `assistant` - Respuestas previas del modelo (para conversaciones multi-turno)
- - `tool` - Resultados de llamadas a funciones (al usar tools)
+ - `assistant` - Respuestas previas del modelo (para conversaciones multiturno)
+ - `tool` - Resultados de llamadas a funciones (al usar herramientas)
-
-
+
Cada solicitud incluye un ID de `model`. Para usar un modelo diferente, cambia el valor de `model` en tu solicitud. Opciones populares:
- - `zai-org-glm-5` - Modelo predeterminado para la mayoría de casos de uso
+
+ - `zai-org-glm-5` - Modelo predeterminado para la mayoría de los casos de uso
- `kimi-k2-6` - Razonamiento sólido para tareas más complejas
- `claude-opus-4-8` - Modelo de alta inteligencia para tareas complejas
- `venice-uncensored-1-2` - Modelo sin censura de Venice
@@ -116,881 +118,270 @@ Empieza a usar la API de Venice en minutos. Genera una API key, haz tu primera s
Explora la lista completa de modelos con precios, capacidades y límites de contexto
-
-
- Puedes optar por activar funciones específicas de Venice como la búsqueda web mediante `venice_parameters`:
+
+ Puedes optar por habilitar funciones específicas de Venice, como la búsqueda web, mediante `venice_parameters`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
Consulta todos los [parámetros disponibles](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
-
+
Transmite respuestas en tiempo real usando `stream=True`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
-
+
Controla cómo responde el modelo con parámetros como temperature, max tokens y más:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
-
- Consulta la [documentación de Chat Completions](/api-reference/endpoint/chat/completions) para más información sobre todos los parámetros admitidos.
-
-
-
----
-
-## Más capacidades
-
-### Generación de imágenes
-
-Crea imágenes a partir de prompts de texto usando modelos de difusión:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**Nota:** la respuesta devuelve imágenes codificadas en base64 en el array `images`. Decodifica la cadena base64 para guardar o mostrar la imagen.
-
-**Modelos de imagen populares:**
-- `qwen-image` - Generación de imágenes de la máxima calidad
-- `venice-sd35` - Opción por defecto, funciona con todas las funciones
-- `hidream` - Generación rápida para uso en producción
-
-
- Mira todos los modelos de imagen disponibles con precios y capacidades
-
-
-Para opciones de parámetros más avanzadas como `cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` y más, consulta la [referencia de la API de imágenes](/api-reference/endpoint/image/generate).
-
-### Edición de imágenes
-
-Modifica imágenes existentes con inpainting impulsado por IA usando el modelo Qwen-Image:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**Nota:** el editor de imágenes utiliza el modelo Qwen-Image y es un endpoint experimental. Envía la imagen de entrada como cadena codificada en base64 y la API devuelve la imagen editada como datos binarios.
-
-Consulta la [API de edición de imágenes](/api-reference/endpoint/image/edit) para todos los parámetros.
-
-### Escalado de imágenes
-
-Mejora y escala imágenes a resoluciones más altas:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**Nota:** envía la imagen de entrada como cadena codificada en base64 y la API devuelve la imagen escalada como datos binarios.
-
-Consulta la [API de escalado de imágenes](/api-reference/endpoint/image/upscale) para todos los parámetros.
-
-### Texto a voz
-
-Convierte texto en audio con más de 50 voces multilingües:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-El modelo `tts-kokoro` admite más de 50 voces multilingües, incluyendo `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` y `jm_kumo`.
-
-Consulta la [API de TTS](/api-reference/endpoint/audio/speech) para todas las opciones de voz.
-
-### Voz a texto
-
-Transcribe archivos de audio a texto:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-Formatos admitidos: WAV, FLAC, MP3, M4A, AAC, MP4. Activa `timestamps=true` para obtener datos de tiempo a nivel de palabra.
-
-Consulta la [API de transcripciones](/api-reference/endpoint/audio/transcriptions) para todas las opciones.
-
-### Embeddings
-
-Genera vectores de embeddings para búsqueda semántica, RAG y recomendaciones:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-Consulta la [API de embeddings](/api-reference/endpoint/embeddings/generate) para procesamiento por lotes y opciones avanzadas.
-
-### Vision (multimodal)
-
-Analiza imágenes junto con texto usando modelos con capacidad de visión como `qwen3-vl-235b-a22b`:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### Function calling
-
-Define funciones que los modelos pueden invocar para interactuar con herramientas y APIs externas:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ Consulta la [documentación de completaciones de chat](/api-reference/endpoint/chat/completions) para obtener más información sobre todos los parámetros admitidos.
+
+
---
## Próximos pasos
-Ahora que ya has hecho tus primeras solicitudes, explora más de lo que ofrece la API de Venice:
+Ahora que has realizado tus primeras solicitudes, explora más de lo que ofrece la API de Venice:
Compara todos los modelos disponibles con sus capacidades, precios y límites de contexto
+
- Explora la documentación detallada de la API con todos los endpoints y parámetros
+ Explora documentación detallada de la API con todos los endpoints y parámetros
+
Aprende a obtener respuestas JSON con esquemas garantizados
+
- Construye con apps de agentes, agentes de programación, herramientas MCP, skills y flujos de trabajo cripto
+ Construye con aplicaciones de agentes, agentes de codificación, herramientas MCP, skills y flujos de trabajo cripto
### Recursos adicionales
-
- Comprende los límites de velocidad y las mejores prácticas para uso en producción
+
+ Comprende los límites de tasa y las mejores prácticas para uso en producción
+
- Referencia para gestionar errores de la API y resolver problemas
+ Referencia para manejar errores de la API y solucionar problemas
+
- Importa nuestra colección completa de Postman para pruebas fáciles
+ Importa nuestra colección completa de Postman para pruebas sencillas
+
- Aprende sobre la arquitectura privacy-first de Venice y el tratamiento de datos
+ Conoce la arquitectura centrada en la privacidad de Venice y el manejo de datos
@@ -998,9 +389,9 @@ Ahora que ya has hecho tus primeras solicitudes, explora más de lo que ofrece l
## ¿Necesitas ayuda?
-- **Comunidad de Discord**: únete a nuestro [servidor de Discord](https://discord.gg/askvenice) para soporte y debates
-- **Documentación**: explora nuestra [referencia completa de la API](/api-reference/api-spec)
-- **Página de estado**: comprueba el estado del servicio en [veniceai-status.com](https://veniceai-status.com)
-- **Twitter**: sigue a [@AskVenice](https://x.com/AskVenice) para actualizaciones
+- **Comunidad de Discord**: Únete a nuestro [servidor de Discord](https://discord.gg/askvenice) para soporte y debates
+- **Documentación**: Explora nuestra [referencia completa de la API](/api-reference/api-spec)
+- **Página de estado**: Consulta el estado del servicio en [veniceai-status.com](https://veniceai-status.com)
+- **Twitter**: Sigue a [@AskVenice](https://x.com/AskVenice) para novedades
diff --git a/fr/overview/getting-started.mdx b/fr/overview/getting-started.mdx
index c5ea1de..2b453e8 100644
--- a/fr/overview/getting-started.mdx
+++ b/fr/overview/getting-started.mdx
@@ -1,21 +1,20 @@
---
-title: Démarrage
-description: "Démarrage rapide pour l'API Venice : générez une clé d'API, envoyez votre première chat completion et explorez les endpoints image, vidéo et audio."
-"og:title": "Démarrage rapide | Venice API Docs"
+title: "Démarrage rapide"
+description: "Démarrage rapide pour l'API Venice — générez une clé API, envoyez votre première complétion de chat et explorez les endpoints d'image, de vidéo et d'audio en quelques minutes."
+og:title: "Démarrage rapide | Documentation de l'API Venice"
---
-Lancez-vous avec l'API Venice en quelques minutes. Générez une clé API, effectuez votre première requête et commencez à construire.
+Prenez en main l'API Venice en quelques minutes. Générez une clé API, effectuez votre première requête et commencez à créer.
## Démarrage rapide
-
- Rendez-vous dans vos [Paramètres API Venice](https://venice.ai/settings/api) et générez une nouvelle clé API.
+
+ Rendez-vous dans vos [paramètres de l'API Venice](https://venice.ai/settings/api) et générez une nouvelle clé API.
- Pour un guide détaillé, consultez le [guide de la clé API](/guides/getting-started/generating-api-key).
+ Pour un guide détaillé, consultez le [guide sur les clés API](/guides/getting-started/generating-api-key).
-
-
+
Ajoutez votre clé API à votre environnement. Vous pouvez l'exporter dans votre shell :
```bash
@@ -28,933 +27,319 @@ Lancez-vous avec l'API Venice en quelques minutes. Générez une clé API, effec
VENICE_API_KEY=your-api-key-here
```
-
-
- Venice est compatible OpenAI, vous pouvez donc utiliser le SDK OpenAI. Si vous préférez utiliser cURL ou des requêtes HTTP brutes, vous pouvez ignorer cette étape.
+
+ Venice est compatible avec OpenAI, vous pouvez donc utiliser le SDK OpenAI. Si vous préférez utiliser cURL ou des requêtes HTTP brutes, vous pouvez ignorer cette étape.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
-
+
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
- **Rôles de message :**
- - `system` - Instructions sur le comportement attendu du modèle
+ **Rôles des messages :**
+
+ - `system` - Instructions sur la manière dont le modèle doit se comporter
- `user` - Vos prompts ou questions
- - `assistant` - Réponses précédentes du modèle (pour les conversations multi-tours)
- - `tool` - Résultats d'appel de fonction (lors de l'utilisation d'outils)
+ - `assistant` - Réponses précédentes du modèle (pour les conversations à plusieurs tours)
+ - `tool` - Résultats d'appels de fonctions (lors de l'utilisation d'outils)
+
+ Chaque requête inclut un ID de `model`. Pour utiliser un modèle différent, modifiez la valeur de `model` dans votre requête. Choix populaires :
-
- Chaque requête inclut un ID `model`. Pour utiliser un modèle différent, modifiez la valeur de `model` dans votre requête. Choix populaires :
- `zai-org-glm-5` - Modèle par défaut pour la plupart des cas d'usage
- - `kimi-k2-6` - Raisonnement solide pour les tâches plus complexes
- - `claude-opus-4-8` - Modèle de haute intelligence pour les tâches complexes
- - `venice-uncensored-1-2` - Le modèle non censuré de Venice
+ - `kimi-k2-6` - Raisonnement solide pour des tâches plus complexes
+ - `claude-opus-4-8` - Modèle à haute intelligence pour les tâches complexes
+ - `venice-uncensored-1-2` - Modèle non censuré de Venice
- Parcourez la liste complète des modèles avec leur tarification, leurs capacités et leurs limites de contexte
+ Parcourez la liste complète des modèles avec leurs tarifs, capacités et limites de contexte
-
-
- Vous pouvez choisir d'activer des fonctionnalités spécifiques à Venice comme la recherche web en utilisant `venice_parameters` :
+
+ Vous pouvez choisir d'activer des fonctionnalités spécifiques à Venice comme la recherche web à l'aide de `venice_parameters` :
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
-
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
- Voir tous les [paramètres disponibles](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
-
- Diffusez les réponses en temps réel en utilisant `stream=True` :
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
-
-
- Contrôlez la façon dont le modèle répond avec des paramètres comme temperature, max tokens et plus :
+ Consultez tous les [paramètres disponibles](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
+
+
+ Diffusez les réponses en temps réel à l'aide de `stream=True` :
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
- Consultez la [doc Chat Completions](/api-reference/endpoint/chat/completions) pour plus d'informations sur tous les paramètres pris en charge.
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
+
-
+
+ Contrôlez la manière dont le modèle répond grâce à des paramètres comme la température, le nombre maximal de tokens, et plus encore :
----
+
-## Autres capacités
-
-### Génération d'image
-
-Créez des images à partir de prompts texte en utilisant des modèles de diffusion :
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**Note :** La réponse renvoie les images encodées en base64 dans le tableau `images`. Décodez la chaîne base64 pour enregistrer ou afficher l'image.
-
-**Modèles d'image populaires :**
-- `qwen-image` - Génération d'image de la plus haute qualité
-- `venice-sd35` - Choix par défaut, fonctionne avec toutes les fonctionnalités
-- `hidream` - Génération rapide pour une utilisation en production
-
-
- Voir tous les modèles d'image disponibles avec leur tarification et leurs capacités
-
-
-Pour des options de paramètres plus avancées comme `cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` et plus, consultez la [référence API Images](/api-reference/endpoint/image/generate).
-
-### Édition d'image
-
-Modifiez des images existantes avec de l'inpainting alimenté par IA en utilisant le modèle Qwen-Image :
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**Note :** L'éditeur d'image utilise le modèle Qwen-Image et est un endpoint expérimental. Envoyez l'image d'entrée sous forme de chaîne encodée en base64, et l'API renvoie l'image éditée sous forme de données binaires.
-
-Voir l'[API Image Edit](/api-reference/endpoint/image/edit) pour tous les paramètres.
-
-### Agrandissement d'image
-
-Améliorez et agrandissez des images vers des résolutions plus élevées :
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**Note :** Envoyez l'image d'entrée sous forme de chaîne encodée en base64, et l'API renvoie l'image agrandie sous forme de données binaires.
-
-Voir l'[API Image Upscale](/api-reference/endpoint/image/upscale) pour tous les paramètres.
-
-### Synthèse vocale (Text-to-Speech)
-
-Convertissez du texte en audio avec plus de 50 voix multilingues :
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-Le modèle `tts-kokoro` prend en charge plus de 50 voix multilingues, dont `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` et `jm_kumo`.
-
-Voir l'[API TTS](/api-reference/endpoint/audio/speech) pour toutes les options de voix.
-
-### Transcription (Speech-to-Text)
-
-Transcrivez des fichiers audio en texte :
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-Formats pris en charge : WAV, FLAC, MP3, M4A, AAC, MP4. Activez `timestamps=true` pour obtenir des données de chronométrage au niveau du mot.
-
-Voir l'[API Transcriptions](/api-reference/endpoint/audio/transcriptions) pour toutes les options.
-
-### Embeddings
-
-Générez des embeddings vectoriels pour la recherche sémantique, le RAG et les recommandations :
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-Voir l'[API Embeddings](/api-reference/endpoint/embeddings/generate) pour le traitement par lots et les options avancées.
-
-### Vision (multimodal)
-
-Analysez des images avec du texte en utilisant des modèles capables de vision comme `qwen3-vl-235b-a22b` :
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### Appels de fonctions
-
-Définissez des fonctions que les modèles peuvent appeler pour interagir avec des outils et API externes :
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ Consultez la [documentation Chat Completions](/api-reference/endpoint/chat/completions) pour plus d'informations sur tous les paramètres pris en charge.
+
+
---
@@ -964,33 +349,39 @@ Maintenant que vous avez effectué vos premières requêtes, explorez davantage
- Comparez tous les modèles disponibles avec leurs capacités, leur tarification et leurs limites de contexte
+ Comparez tous les modèles disponibles avec leurs capacités, tarifs et limites de contexte
-
- Explorez la documentation API détaillée avec tous les endpoints et paramètres
+
+
+ Explorez la documentation détaillée de l'API avec tous les endpoints et paramètres
+
Apprenez à obtenir des réponses JSON avec des schémas garantis
-
- Construisez avec des applications d'agent, des agents de codage, des outils MCP, des skills et des workflows crypto
+
+
+ Créez avec des applications d'agent, des agents de code, des outils MCP, des compétences et des workflows crypto
### Ressources supplémentaires
-
+
Comprenez les limites de débit et les bonnes pratiques pour une utilisation en production
+
- Référence pour gérer les erreurs API et résoudre les problèmes
+ Référence pour la gestion des erreurs de l'API et le dépannage
+
- Importez notre collection Postman complète pour tester facilement
+ Importez notre collection Postman complète pour des tests faciles
+
- Découvrez l'architecture privacy-first de Venice et la gestion des données
+ Découvrez l'architecture axée sur la confidentialité de Venice et la gestion des données
@@ -998,8 +389,8 @@ Maintenant que vous avez effectué vos premières requêtes, explorez davantage
## Besoin d'aide ?
-- **Communauté Discord** : Rejoignez notre [serveur Discord](https://discord.gg/askvenice) pour le support et les discussions
-- **Documentation** : Parcourez notre [référence API complète](/api-reference/api-spec)
+- **Communauté Discord** : Rejoignez notre [serveur Discord](https://discord.gg/askvenice) pour obtenir de l'aide et participer aux discussions
+- **Documentation** : Parcourez notre [référence complète de l'API](/api-reference/api-spec)
- **Page de statut** : Vérifiez l'état du service sur [veniceai-status.com](https://veniceai-status.com)
- **Twitter** : Suivez [@AskVenice](https://x.com/AskVenice) pour les mises à jour
diff --git a/it/overview/getting-started.mdx b/it/overview/getting-started.mdx
index f03e10a..8a1f80c 100644
--- a/it/overview/getting-started.mdx
+++ b/it/overview/getting-started.mdx
@@ -1,335 +1,340 @@
---
-title: Per iniziare
-description: "Quickstart per l'API Venice — genera una chiave API, invia la tua prima chat completion ed esplora gli endpoint immagini, video e audio in pochi minuti."
-"og:title": "Quickstart | Venice API Docs"
+title: "Guida rapida"
+description: "Guida rapida per la Venice API — genera una chiave API, invia il tuo primo chat completion ed esplora gli endpoint per immagini, video e audio in pochi minuti."
+og:title: "Guida rapida | Documentazione Venice API"
---
-Inizia a usare l'API Venice in pochi minuti. Genera una API key, esegui la tua prima richiesta e comincia a sviluppare.
+Inizia a usare la Venice API in pochi minuti. Genera una chiave API, effettua la tua prima richiesta e comincia a costruire.
-## Quickstart
+## Guida rapida
-
- Vai nelle tue [impostazioni API di Venice](https://venice.ai/settings/api) e genera una nuova API key.
+
+ Vai alle [Impostazioni API di Venice](https://venice.ai/settings/api) e genera una nuova chiave API.
- Per una guida dettagliata, consulta la [guida alle API key](/guides/getting-started/generating-api-key).
+ Per una guida dettagliata, consulta la [guida alla chiave API](/guides/getting-started/generating-api-key).
-
-
- Aggiungi la tua API key all'ambiente. Puoi esportarla nella shell:
+
+ Aggiungi la tua chiave API al tuo ambiente. Puoi esportarla nella tua shell:
```bash
export VENICE_API_KEY='your-api-key-here'
```
- Oppure aggiungerla a un file `.env` nel tuo progetto:
+ Oppure aggiungila a un file `.env` nel tuo progetto:
```bash
VENICE_API_KEY=your-api-key-here
```
-
- Venice è compatibile con OpenAI, quindi puoi usare l'SDK OpenAI. Se preferisci usare cURL o richieste HTTP raw, puoi saltare questo passaggio.
+ Venice è compatibile con OpenAI, quindi puoi usare l'SDK OpenAI. Se preferisci usare cURL o richieste HTTP grezze, puoi saltare questo passaggio.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
**Ruoli dei messaggi:**
- - `system` - Istruzioni su come il modello deve comportarsi
+
+ - `system` - Istruzioni su come il modello dovrebbe comportarsi
- `user` - I tuoi prompt o domande
- - `assistant` - Risposte precedenti del modello (per conversazioni multi-turno)
- - `tool` - Risultati delle chiamate a funzione (quando usi i tool)
+ - `assistant` - Risposte precedenti del modello (per conversazioni a più turni)
+ - `tool` - Risultati delle chiamate di funzione (quando si usano gli strumenti)
+
+ Ogni richiesta include un ID `model`. Per usare un modello diverso, cambia il valore `model` nella tua richiesta. Scelte popolari:
-
- Ogni richiesta include un `model` ID. Per usare un modello diverso, cambia il valore di `model` nella richiesta. Scelte comuni:
- `zai-org-glm-5` - Modello predefinito per la maggior parte dei casi d'uso
- - `kimi-k2-6` - Reasoning solido per attività più complesse
- - `claude-opus-4-8` - Modello ad alta intelligenza per task complessi
- - `venice-uncensored-1-2` - Modello uncensored di Venice
+ - `kimi-k2-6` - Forte capacità di ragionamento per compiti più complessi
+ - `claude-opus-4-8` - Modello ad alta intelligenza per compiti complessi
+ - `venice-uncensored-1-2` - Il modello senza censura di Venice
Sfoglia l'elenco completo dei modelli con prezzi, capacità e limiti di contesto
-
-
- Puoi scegliere di abilitare funzionalità specifiche di Venice come la web search tramite `venice_parameters`:
+
+ Puoi scegliere di abilitare funzionalità specifiche di Venice come la ricerca web usando `venice_parameters`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
- Consulta tutti i [parametri disponibili](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
+ Vedi tutti i [parametri disponibili](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
Trasmetti le risposte in tempo reale usando `stream=True`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
Controlla come il modello risponde con parametri come temperature, max tokens e altri:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
+ }
+ }'
+ ```
+
Consulta la [documentazione di Chat Completions](/api-reference/endpoint/chat/completions) per maggiori informazioni su tutti i parametri supportati.
@@ -338,657 +343,43 @@ Inizia a usare l'API Venice in pochi minuti. Genera una API key, esegui la tua p
---
-## Altre capacità
-
-### Generazione di immagini
-
-Crea immagini da prompt testuali usando modelli di diffusione:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**Nota:** la risposta restituisce immagini codificate in base64 nell'array `images`. Decodifica la stringa base64 per salvare o visualizzare l'immagine.
-
-**Modelli di immagini popolari:**
-- `qwen-image` - Generazione di immagini di altissima qualità
-- `venice-sd35` - Scelta predefinita, funziona con tutte le funzionalità
-- `hidream` - Generazione veloce per uso in produzione
-
-
- Vedi tutti i modelli di immagini disponibili con prezzi e capacità
-
-
-Per opzioni di parametri più avanzate come `cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` e altre, consulta la [Images API Reference](/api-reference/endpoint/image/generate).
-
-### Editing di immagini
-
-Modifica immagini esistenti con inpainting basato su AI tramite il modello Qwen-Image:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**Nota:** l'editor di immagini usa il modello Qwen-Image ed è un endpoint sperimentale. Invia l'immagine di input come stringa codificata in base64; l'API restituisce l'immagine modificata come dati binari.
-
-Consulta la [Image Edit API](/api-reference/endpoint/image/edit) per tutti i parametri.
-
-### Upscaling di immagini
-
-Migliora le immagini portandole a risoluzioni più alte:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**Nota:** invia l'immagine di input come stringa codificata in base64; l'API restituisce l'immagine con upscaling come dati binari.
-
-Consulta la [Image Upscale API](/api-reference/endpoint/image/upscale) per tutti i parametri.
-
-### Text-to-Speech
-
-Converti testo in audio con oltre 50 voci multilingue:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-Il modello `tts-kokoro` supporta oltre 50 voci multilingue, tra cui `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` e `jm_kumo`.
-
-Consulta la [TTS API](/api-reference/endpoint/audio/speech) per tutte le opzioni di voce.
-
-### Speech-to-Text
-
-Trascrivi file audio in testo:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-Formati supportati: WAV, FLAC, MP3, M4A, AAC, MP4. Abilita `timestamps=true` per ottenere dati di timing a livello di parola.
-
-Consulta la [Transcriptions API](/api-reference/endpoint/audio/transcriptions) per tutte le opzioni.
-
-### Embeddings
-
-Genera vector embedding per ricerca semantica, RAG e raccomandazioni:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-Consulta la [Embeddings API](/api-reference/endpoint/embeddings/generate) per l'elaborazione batch e le opzioni avanzate.
-
-### Vision (multimodale)
-
-Analizza immagini insieme al testo usando modelli vision-capable come `qwen3-vl-235b-a22b`:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
- }
- ]
- }
- ]
- }'
- ```
-
-
-### Function calling
-
-Definisci funzioni che i modelli possono chiamare per interagire con tool e API esterni:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
- }
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
- }'
- ```
-
-
----
+## Passi successivi
-## Prossimi passi
-
-Ora che hai eseguito le prime richieste, esplora tutto ciò che l'API Venice ha da offrire:
+Ora che hai effettuato le tue prime richieste, esplora tutto ciò che la Venice API ha da offrire:
- Confronta tutti i modelli disponibili con capacità, prezzi e limiti di contesto
+ Confronta tutti i modelli disponibili con le loro capacità, prezzi e limiti di contesto
-
+
+
Esplora la documentazione dettagliata dell'API con tutti gli endpoint e i parametri
+
Scopri come ottenere risposte JSON con schemi garantiti
-
- Sviluppa con app per agent, coding agent, tool MCP, skill e workflow crypto
+
+
+ Costruisci con app di agenti, agenti di codifica, strumenti MCP, skill e workflow crypto
### Risorse aggiuntive
-
- Comprendi i rate limit e le best practice per l'uso in produzione
+
+ Comprendi i limiti di frequenza e le best practice per l'uso in produzione
+
Riferimento per gestire gli errori dell'API e risolvere i problemi
-
- Importa la nostra collection Postman completa per testare facilmente
+
+
+ Importa la nostra collezione Postman completa per test facili
+
Scopri l'architettura privacy-first di Venice e la gestione dei dati
@@ -998,9 +389,9 @@ Ora che hai eseguito le prime richieste, esplora tutto ciò che l'API Venice ha
## Hai bisogno di aiuto?
-- **Community Discord**: unisciti al nostro [server Discord](https://discord.gg/askvenice) per supporto e discussioni
-- **Documentazione**: sfoglia la nostra [API reference completa](/api-reference/api-spec)
-- **Status page**: controlla lo stato del servizio su [veniceai-status.com](https://veniceai-status.com)
-- **Twitter**: segui [@AskVenice](https://x.com/AskVenice) per gli aggiornamenti
+- **Comunità Discord**: Unisciti al nostro [server Discord](https://discord.gg/askvenice) per supporto e discussioni
+- **Documentazione**: Sfoglia il nostro [riferimento API completo](/api-reference/api-spec)
+- **Pagina di stato**: Controlla lo stato del servizio su [veniceai-status.com](https://veniceai-status.com)
+- **Twitter**: Segui [@AskVenice](https://x.com/AskVenice) per gli aggiornamenti
diff --git a/ko/overview/getting-started.mdx b/ko/overview/getting-started.mdx
index a1f4737..e87600e 100644
--- a/ko/overview/getting-started.mdx
+++ b/ko/overview/getting-started.mdx
@@ -1,22 +1,21 @@
---
-title: 시작하기
-description: "Venice API 빠른 시작 — API 키를 발급받고, 첫 chat completion을 보내고, 이미지·비디오·오디오 엔드포인트를 몇 분 만에 살펴보세요."
-"og:title": "Quickstart | Venice API Docs"
+title: "빠른 시작"
+description: "Venice API 빠른 시작 가이드 — API 키를 생성하고, 첫 채팅 완성 요청을 보내고, 이미지, 비디오, 오디오 엔드포인트를 몇 분 안에 살펴보세요."
+og:title: "빠른 시작 | Venice API 문서"
---
-몇 분 안에 Venice API를 시작하고 실행해보세요. API 키를 발급받고, 첫 요청을 보내고, 빌드를 시작하세요.
+Venice API를 몇 분 안에 시작해보세요. API 키를 생성하고, 첫 요청을 보내고, 개발을 시작하세요.
## 빠른 시작
- [Venice API 설정](https://venice.ai/settings/api)으로 이동해 새 API 키를 생성합니다.
+ [Venice API 설정](https://venice.ai/settings/api)으로 이동하여 새 API 키를 생성하세요.
- 자세한 가이드는 [API 키 가이드](/guides/getting-started/generating-api-key)를 참고하세요.
+ 자세한 안내는 [API 키 가이드](/guides/getting-started/generating-api-key)를 확인하세요.
-
-
- API 키를 환경변수에 추가합니다. 셸에서 export할 수 있습니다:
+
+ 환경에 API 키를 추가하세요. 셸에서 export할 수 있습니다:
```bash
export VENICE_API_KEY='your-api-key-here'
@@ -28,969 +27,361 @@ description: "Venice API 빠른 시작 — API 키를 발급받고, 첫 chat com
VENICE_API_KEY=your-api-key-here
```
-
-
- Venice는 OpenAI 호환이므로 OpenAI SDK를 그대로 사용할 수 있습니다. cURL이나 raw HTTP 요청을 선호한다면 이 단계는 건너뛰어도 됩니다.
+
+ Venice는 OpenAI 호환이므로 OpenAI SDK를 사용할 수 있습니다. cURL이나 원시 HTTP 요청을 사용하는 것을 선호한다면 이 단계를 건너뛸 수 있습니다.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
- **메시지 역할(role):**
+ **메시지 역할:**
+
- `system` - 모델이 어떻게 동작해야 하는지에 대한 지침
- - `user` - 사용자의 prompt 또는 질문
- - `assistant` - 이전 모델 응답(멀티턴 대화용)
- - `tool` - 함수 호출 결과(도구 사용 시)
+ - `user` - 여러분의 프롬프트 또는 질문
+ - `assistant` - 이전 모델 응답 (멀티턴 대화용)
+ - `tool` - 함수 호출 결과 (도구 사용 시)
+
+ 모든 요청에는 `model` ID가 포함됩니다. 다른 모델을 사용하려면 요청의 `model` 값을 변경하세요. 인기 있는 선택지:
-
- 모든 요청에는 `model` ID가 포함됩니다. 다른 모델을 사용하려면 요청의 `model` 값을 변경하세요. 자주 쓰이는 선택지:
- - `zai-org-glm-5` - 대부분의 사용 사례를 위한 기본 모델
- - `kimi-k2-6` - 복잡한 작업에 강한 추론 능력
+ - `zai-org-glm-5` - 대부분의 사용 사례에 적합한 기본 모델
+ - `kimi-k2-6` - 더 복잡한 작업을 위한 강력한 추론 능력
- `claude-opus-4-8` - 복잡한 작업을 위한 고지능 모델
- - `venice-uncensored-1-2` - Venice의 검열되지 않은(uncensored) 모델
+ - `venice-uncensored-1-2` - Venice의 검열되지 않은 모델
- 가격, 기능, context 한도와 함께 전체 모델 목록을 확인하세요
+ 가격, 기능, 컨텍스트 제한과 함께 모든 모델의 전체 목록을 살펴보세요
-
-
- `venice_parameters`를 사용해 웹 검색 같은 Venice 전용 기능을 활성화할 수 있습니다:
+
+ `venice_parameters`를 사용하여 웹 검색과 같은 Venice 전용 기능을 활성화할 수 있습니다:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
-
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
- [사용 가능한 모든 파라미터](https://docs.venice.ai/api-reference/api-spec#venice-parameters)를 확인하세요.
-
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
-
- `stream=True`를 사용해 응답을 실시간으로 스트리밍합니다:
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
-
-
- temperature, max tokens 등 다양한 파라미터로 모델 응답 방식을 제어하세요:
+ 모든 [사용 가능한 매개변수](https://docs.venice.ai/api-reference/api-spec#venice-parameters)를 확인하세요.
+
+
+ `stream=True`를 사용하여 응답을 실시간으로 스트리밍하세요:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
- 지원되는 모든 파라미터에 대한 자세한 내용은 [Chat Completions 문서](/api-reference/endpoint/chat/completions)를 확인하세요.
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
+
-
+
+ temperature, max tokens 등의 매개변수로 모델의 응답 방식을 제어하세요:
----
+
-## 더 많은 기능
-
-### 이미지 생성
-
-확산(diffusion) 모델로 텍스트 prompt에서 이미지를 생성합니다:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**참고:** 응답은 `images` 배열에 base64로 인코딩된 이미지를 반환합니다. base64 문자열을 디코딩해 이미지를 저장하거나 표시하세요.
-
-**인기 있는 이미지 모델:**
-- `qwen-image` - 가장 높은 품질의 이미지 생성
-- `venice-sd35` - 기본 선택, 모든 기능과 호환
-- `hidream` - 프로덕션 환경을 위한 빠른 생성
-
-
- 가격과 기능과 함께 사용 가능한 모든 이미지 모델을 확인하세요
-
-
-`cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` 등 더 고급 파라미터 옵션은 [Images API 레퍼런스](/api-reference/endpoint/image/generate)를 참고하세요.
-
-### 이미지 편집
-
-Qwen-Image 모델을 활용한 AI 기반 인페인팅으로 기존 이미지를 수정합니다:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**참고:** 이미지 편집기는 Qwen-Image 모델을 사용하며 실험적 endpoint입니다. 입력 이미지는 base64로 인코딩된 문자열로 보내고, API는 편집된 이미지를 바이너리 데이터로 반환합니다.
-
-모든 파라미터는 [Image Edit API](/api-reference/endpoint/image/edit)를 참고하세요.
-
-### 이미지 업스케일링
-
-이미지를 더 높은 해상도로 향상시키고 업스케일링합니다:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**참고:** 입력 이미지는 base64로 인코딩된 문자열로 보내고, API는 업스케일된 이미지를 바이너리 데이터로 반환합니다.
-
-모든 파라미터는 [Image Upscale API](/api-reference/endpoint/image/upscale)를 참고하세요.
-
-### Text-to-Speech
-
-50개 이상의 다국어 음성으로 텍스트를 음성으로 변환합니다:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-`tts-kokoro` 모델은 `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei`, `jm_kumo` 등 50개 이상의 다국어 음성을 지원합니다.
-
-모든 음성 옵션은 [TTS API](/api-reference/endpoint/audio/speech)를 참고하세요.
-
-### Speech-to-Text
-
-오디오 파일을 텍스트로 전사합니다:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-지원 포맷: WAV, FLAC, MP3, M4A, AAC, MP4. 단어 단위 타이밍 데이터가 필요하면 `timestamps=true`를 활성화하세요.
-
-모든 옵션은 [Transcriptions API](/api-reference/endpoint/audio/transcriptions)를 참고하세요.
-
-### 임베딩(Embeddings)
-
-시맨틱 검색, RAG, 추천 등을 위한 벡터 임베딩을 생성합니다:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-배치 처리와 고급 옵션은 [Embeddings API](/api-reference/endpoint/embeddings/generate)를 참고하세요.
-
-### 비전(멀티모달)
-
-`qwen3-vl-235b-a22b` 같은 비전 지원 모델을 사용해 이미지와 텍스트를 함께 분석합니다:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### 함수 호출(Function Calling)
-
-모델이 외부 도구와 API와 상호작용하기 위해 호출할 수 있는 함수를 정의합니다:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ 지원되는 모든 매개변수에 대한 자세한 내용은 [Chat Completions 문서](/api-reference/endpoint/chat/completions)를 확인하세요.
+
+
---
## 다음 단계
-첫 요청을 보내봤다면, Venice API의 더 많은 기능을 살펴보세요:
+첫 요청을 완료했으니, Venice API가 제공하는 더 많은 기능을 살펴보세요:
- 사용 가능한 모든 모델의 기능, 가격, context 한도를 비교하세요
+ 사용 가능한 모든 모델의 기능, 가격, 컨텍스트 제한을 비교하세요
+
- 모든 endpoint와 파라미터가 포함된 상세 API 문서를 살펴보세요
+ 모든 엔드포인트와 매개변수에 대한 자세한 API 문서를 살펴보세요
+
- 스키마가 보장되는 JSON 응답을 받는 방법을 알아보세요
+ 보장된 스키마로 JSON 응답을 받는 방법을 알아보세요
+
- 에이전트 앱, 코딩 에이전트, MCP 도구, 스킬, 크립토 워크플로로 빌드하세요
+ 에이전트 앱, 코딩 에이전트, MCP 도구, 스킬, 암호화폐 워크플로우를 구축하세요
-### 추가 리소스
+### 추가 자료
-
- rate limit과 프로덕션 사용 모범 사례를 이해하세요
+
+ 프로덕션 사용을 위한 속도 제한과 모범 사례를 이해하세요
-
- API 에러 처리 및 문제 해결을 위한 레퍼런스
+
+
+ API 오류 처리 및 문제 해결에 대한 참고 자료
+
- 간편한 테스트를 위해 완전한 Postman 컬렉션을 임포트하세요
+ 간편한 테스트를 위해 전체 Postman 컬렉션을 가져오세요
+
- Venice의 프라이버시 우선 아키텍처와 데이터 처리 방식을 알아보세요
+ Venice의 프라이버시 우선 아키텍처와 데이터 처리 방식에 대해 알아보세요
@@ -998,9 +389,9 @@ Qwen-Image 모델을 활용한 AI 기반 인페인팅으로 기존 이미지를
## 도움이 필요하신가요?
-- **Discord 커뮤니티**: [Discord 서버](https://discord.gg/askvenice)에 참여해 지원과 토론을 받으세요
-- **문서**: [완전한 API 레퍼런스](/api-reference/api-spec)를 살펴보세요
+- **Discord 커뮤니티**: 지원과 토론을 위해 [Discord 서버](https://discord.gg/askvenice)에 참여하세요
+- **문서**: [전체 API 레퍼런스](/api-reference/api-spec)를 살펴보세요
- **상태 페이지**: [veniceai-status.com](https://veniceai-status.com)에서 서비스 상태를 확인하세요
-- **Twitter**: 업데이트는 [@AskVenice](https://x.com/AskVenice)를 팔로우하세요
+- **Twitter**: 업데이트를 위해 [@AskVenice](https://x.com/AskVenice)를 팔로우하세요
diff --git a/pt-BR/overview/getting-started.mdx b/pt-BR/overview/getting-started.mdx
index bcfcb82..df7695c 100644
--- a/pt-BR/overview/getting-started.mdx
+++ b/pt-BR/overview/getting-started.mdx
@@ -1,20 +1,19 @@
---
-title: Primeiros passos
-description: "Início rápido da Venice API — gere uma chave de API, envie sua primeira chat completion e explore os endpoints de imagem, vídeo e áudio em minutos."
-"og:title": "Início rápido | Documentação da API Venice"
+title: "Guia rápido"
+description: "Guia rápido para a API Venice — gere uma chave de API, envie sua primeira conclusão de chat e explore endpoints de imagem, vídeo e áudio em minutos."
+og:title: "Guia rápido | Documentação da API Venice"
---
Comece a usar a API Venice em minutos. Gere uma chave de API, faça sua primeira requisição e comece a construir.
-## Início rápido
+## Guia rápido
- Vá até suas [Configurações da API Venice](https://venice.ai/settings/api) e gere uma nova chave de API.
+ Acesse as [Configurações da API Venice](https://venice.ai/settings/api) e gere uma nova chave de API.
- Para um passo a passo detalhado, confira o [guia de chave de API](/guides/getting-started/generating-api-key).
+ Para um tutorial detalhado, confira o [guia de Chave de API](/guides/getting-started/generating-api-key).
-
Adicione sua chave de API ao seu ambiente. Você pode exportá-la no seu shell:
@@ -22,91 +21,94 @@ Comece a usar a API Venice em minutos. Gere uma chave de API, faça sua primeira
export VENICE_API_KEY='your-api-key-here'
```
- Ou adicione-a a um arquivo `.env` no seu projeto:
+ Ou adicioná-la a um arquivo `.env` no seu projeto:
```bash
VENICE_API_KEY=your-api-key-here
```
-
- A Venice é compatível com a OpenAI, então você pode usar o SDK da OpenAI. Se preferir usar cURL ou requisições HTTP brutas, pode pular este passo.
+ A Venice é compatível com a OpenAI, então você pode usar o SDK da OpenAI. Se preferir usar cURL ou requisições HTTP puras, você pode pular esta etapa.
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
- **Papéis de mensagem:**
- - `system` - Instruções de como o modelo deve se comportar
+ **Funções das mensagens:**
+
+ - `system` - Instruções sobre como o modelo deve se comportar
- `user` - Seus prompts ou perguntas
- - `assistant` - Respostas anteriores do modelo (para conversas com múltiplos turnos)
+ - `assistant` - Respostas anteriores do modelo (para conversas de múltiplos turnos)
- `tool` - Resultados de chamadas de função (ao usar ferramentas)
-
- Toda requisição inclui um `model` ID. Para usar um modelo diferente, altere o valor de `model` na sua requisição. Escolhas populares:
+ Cada requisição inclui um ID de `model`. Para usar um modelo diferente, altere o valor de `model` na sua requisição. Escolhas populares:
+
- `zai-org-glm-5` - Modelo padrão para a maioria dos casos de uso
- `kimi-k2-6` - Raciocínio forte para tarefas mais complexas
- `claude-opus-4-8` - Modelo de alta inteligência para tarefas complexas
@@ -116,864 +118,250 @@ Comece a usar a API Venice em minutos. Gere uma chave de API, faça sua primeira
Navegue pela lista completa de modelos com preços, capacidades e limites de contexto
-
- Você pode optar por habilitar recursos específicos da Venice como busca na web usando `venice_parameters`:
+ Você pode optar por ativar recursos específicos da Venice, como busca na web, usando `venice_parameters`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
Veja todos os [parâmetros disponíveis](https://docs.venice.ai/api-reference/api-spec#venice-parameters).
-
-
+
Faça streaming das respostas em tempo real usando `stream=True`:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
- Controle como o modelo responde com parâmetros como temperature, max tokens e mais:
+ Controle como o modelo responde com parâmetros como temperature, max tokens e outros:
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
-
- Confira a documentação de [Chat Completions](/api-reference/endpoint/chat/completions) para mais informações sobre todos os parâmetros suportados.
-
-
-
----
-
-## Mais capacidades
-
-### Geração de imagens
-
-Crie imagens a partir de prompts de texto usando modelos de difusão:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**Nota:** A resposta retorna imagens codificadas em base64 no array `images`. Decodifique a string base64 para salvar ou exibir a imagem.
-
-**Modelos de imagem populares:**
-- `qwen-image` - Geração de imagem da mais alta qualidade
-- `venice-sd35` - Escolha padrão, funciona com todos os recursos
-- `hidream` - Geração rápida para uso em produção
-
-
- Veja todos os modelos de imagem disponíveis com preços e capacidades
-
-
-Para opções de parâmetros mais avançadas como `cfg_scale`, `negative_prompt`, `style_preset`, `seed`, `variants` e mais, confira a [referência da API de imagens](/api-reference/endpoint/image/generate).
-
-### Edição de imagem
-
-Modifique imagens existentes com inpainting com IA usando o modelo Qwen-Image:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**Nota:** O editor de imagens usa o modelo Qwen-Image e é um endpoint experimental. Envie a imagem de entrada como uma string codificada em base64, e a API retornará a imagem editada como dados binários.
-
-Veja a [API de edição de imagens](/api-reference/endpoint/image/edit) para todos os parâmetros.
-
-### Upscaling de imagem
-
-Aprimore e faça upscale de imagens para resoluções mais altas:
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**Nota:** Envie a imagem de entrada como uma string codificada em base64, e a API retornará a imagem com upscale como dados binários.
-
-Veja a [API de upscale de imagem](/api-reference/endpoint/image/upscale) para todos os parâmetros.
-
-### Texto para fala
-
-Converta texto em áudio com mais de 50 vozes multilíngues:
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-O modelo `tts-kokoro` suporta mais de 50 vozes multilíngues, incluindo `af_sky`, `af_nova`, `am_liam`, `bf_emma`, `zf_xiaobei` e `jm_kumo`.
-
-Veja a [API de TTS](/api-reference/endpoint/audio/speech) para todas as opções de voz.
-
-### Fala para texto
-
-Transcreva arquivos de áudio em texto:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-Formatos suportados: WAV, FLAC, MP3, M4A, AAC, MP4. Habilite `timestamps=true` para obter dados de tempo no nível de palavra.
-
-Veja a [API de transcrições](/api-reference/endpoint/audio/transcriptions) para todas as opções.
-
-### Embeddings
-
-Gere embeddings vetoriais para busca semântica, RAG e recomendações:
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-Veja a [API de embeddings](/api-reference/endpoint/embeddings/generate) para processamento em lote e opções avançadas.
-
-### Visão (multimodal)
-
-Analise imagens junto com texto usando modelos com capacidade de visão como `qwen3-vl-235b-a22b`:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### Function calling
-
-Defina funções que os modelos podem chamar para interagir com ferramentas e APIs externas:
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ Confira a [documentação de Chat Completions](/api-reference/endpoint/chat/completions) para mais informações sobre todos os parâmetros suportados.
+
+
---
## Próximos passos
-Agora que você fez suas primeiras requisições, explore mais do que a API Venice oferece:
+Agora que você fez suas primeiras requisições, explore mais do que a API Venice tem a oferecer:
-
+
Compare todos os modelos disponíveis com suas capacidades, preços e limites de contexto
+
Explore a documentação detalhada da API com todos os endpoints e parâmetros
+
- Aprenda a obter respostas em JSON com schemas garantidos
+ Aprenda como obter respostas em JSON com esquemas garantidos
+
- Construa com apps de agente, agentes de programação, ferramentas MCP, skills e fluxos cripto
+ Construa com apps de agentes, agentes de programação, ferramentas MCP, skills e fluxos de trabalho cripto
@@ -983,14 +371,17 @@ Agora que você fez suas primeiras requisições, explore mais do que a API Veni
Entenda os limites de taxa e as melhores práticas para uso em produção
+
- Referência para tratar erros da API e solucionar problemas
+ Referência para lidar com erros da API e solucionar problemas
+
- Importe nossa coleção completa do Postman para testes fáceis
+ Importe nossa coleção completa do Postman para facilitar os testes
+
- Saiba mais sobre a arquitetura privacy-first da Venice e o tratamento de dados
+ Saiba mais sobre a arquitetura da Venice, que prioriza a privacidade, e o tratamento de dados
diff --git a/zh/overview/getting-started.mdx b/zh/overview/getting-started.mdx
index 5e93c62..22ee0fe 100644
--- a/zh/overview/getting-started.mdx
+++ b/zh/overview/getting-started.mdx
@@ -1,996 +1,387 @@
---
-title: 开始使用
-description: "Venice API 快速上手 —— 生成 API 密钥、发送您的第一个 chat completion，并在几分钟内探索图像、视频和音频端点。"
-"og:title": "Quickstart | Venice API Docs"
+title: "快速开始"
+description: "Venice API 快速开始指南 —— 生成 API 密钥、发送首个聊天补全请求，并在几分钟内探索图像、视频和音频端点。"
+og:title: "快速开始 | Venice API 文档"
---
-在几分钟内启动并运行 Venice API。生成 API 密钥、发出您的第一个请求，并开始构建。
+在几分钟内上手使用 Venice API。生成 API 密钥，发起首个请求，开始构建。
## 快速开始
- 前往您的 [Venice API 设置](https://venice.ai/settings/api) 并生成新的 API 密钥。
+ 前往您的 [Venice API 设置](https://venice.ai/settings/api) 生成一个新的 API 密钥。
- 如需详细的操作指南，请查看 [API 密钥指南](/guides/getting-started/generating-api-key)。
+ 如需详细的操作指导，请查阅 [API 密钥指南](/guides/getting-started/generating-api-key)。
-
-
- 将您的 API 密钥添加到您的环境中。您可以在 shell 中导出它：
+
+ 将您的 API 密钥添加到环境变量中。您可以在 shell 中导出：
```bash
export VENICE_API_KEY='your-api-key-here'
```
- 或将其添加到项目中的 `.env` 文件：
+ 或将其添加到项目的 `.env` 文件中：
```bash
VENICE_API_KEY=your-api-key-here
```
-
- Venice 与 OpenAI 兼容，因此您可以使用 OpenAI SDK。如果您更喜欢使用 cURL 或原始 HTTP 请求，可以跳过此步骤。
+ Venice 兼容 OpenAI，因此您可以直接使用 OpenAI SDK。如果您更愿意使用 cURL 或原始 HTTP 请求，可以跳过此步骤。
- ```bash Python
- pip install openai
- ```
- ```bash Node.js
- npm install openai
- ```
+ ```bash Python
+ pip install openai
+ ```
+
+ ```bash Node.js
+ npm install openai
+ ```
+
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a helpful AI assistant"},
- {"role": "user", "content": "Why is privacy important?"}
- ]
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a helpful AI assistant' },
- { role: 'user', content: 'Why is privacy important?' }
- ]
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.getenv("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a helpful AI assistant"},
{"role": "user", "content": "Why is privacy important?"}
- ]
- }'
- ```
+ ]
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a helpful AI assistant' },
+ { role: 'user', content: 'Why is privacy important?' }
+ ]
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a helpful AI assistant"},
+ {"role": "user", "content": "Why is privacy important?"}
+ ]
+ }'
+ ```
+
**消息角色：**
- - `system` - 模型应如何表现的指令
- - `user` - 您的 prompt 或问题
- - `assistant` - 之前的模型响应（用于多轮对话）
- - `tool` - 函数调用结果（使用工具时）
-
+ - `system` - 关于模型应如何表现的指令
+ - `user` - 您的提示或问题
+ - `assistant` - 模型此前的回复（用于多轮对话）
+ - `tool` - 函数调用结果（在使用工具时）
+
- 每个请求都包含一个 `model` ID。要使用不同的模型，请更改请求中的 `model` 值。热门选择：
- - `zai-org-glm-5` - 大多数用例的默认模型
- - `kimi-k2-6` - 适用于更复杂任务的强大推理
+ 每个请求都包含一个 `model` ID。要使用不同的模型，请更改请求中的 `model` 值。常用选择：
+
+ - `zai-org-glm-5` - 适用于大多数场景的默认模型
+ - `kimi-k2-6` - 面向更复杂任务的强推理能力
- `claude-opus-4-8` - 适用于复杂任务的高智能模型
- `venice-uncensored-1-2` - Venice 的无审查模型
- 浏览包含定价、能力和上下文限制的完整模型列表
+ 浏览完整的模型列表，包含价格、能力和上下文限制
-
- 您可以选择使用 `venice_parameters` 启用 Venice 特有的功能，如网页搜索：
+ 您可以选择通过 `venice_parameters` 启用 Venice 特有功能，例如网页搜索：
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "user", "content": "What are the latest developments in AI?"}
- ],
- extra_body={
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": True
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'user', content: 'What are the latest developments in AI?' }
- ],
- venice_parameters: {
- enable_web_search: 'auto',
- include_venice_system_prompt: true
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
- ],
- "venice_parameters": {
- "enable_web_search": "auto",
- "include_venice_system_prompt": true
- }
- }'
- ```
+ ],
+ extra_body={
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": True
+ }
+ }
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'user', content: 'What are the latest developments in AI?' }
+ ],
+ venice_parameters: {
+ enable_web_search: 'auto',
+ include_venice_system_prompt: true
+ }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "What are the latest developments in AI?"}
+ ],
+ "venice_parameters": {
+ "enable_web_search": "auto",
+ "include_venice_system_prompt": true
+ }
+ }'
+ ```
+
查看所有[可用参数](https://docs.venice.ai/api-reference/api-spec#venice-parameters)。
-
- 使用 `stream=True` 实时流式传输响应：
+ 使用 `stream=True` 实时流式获取响应：
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- stream = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "Write a short story about AI"}],
- stream=True
- )
-
- for chunk in stream:
- if chunk.choices and chunk.choices[0].delta.content is not None:
- print(chunk.choices[0].delta.content, end="")
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const stream = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: 'Write a short story about AI' }],
- stream: true
- });
-
- for await (const chunk of stream) {
- if (chunk.choices && chunk.choices[0]?.delta?.content) {
- process.stdout.write(chunk.choices[0].delta.content);
- }
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {"role": "user", "content": "Write a short story about AI"}
- ],
- "stream": true
- }'
- ```
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ stream = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[{"role": "user", "content": "Write a short story about AI"}],
+ stream=True
+ )
+
+ for chunk in stream:
+ if chunk.choices and chunk.choices[0].delta.content is not None:
+ print(chunk.choices[0].delta.content, end="")
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const stream = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [{ role: 'user', content: 'Write a short story about AI' }],
+ stream: true
+ });
+
+ for await (const chunk of stream) {
+ if (chunk.choices && chunk.choices[0]?.delta?.content) {
+ process.stdout.write(chunk.choices[0].delta.content);
+ }
+ }
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "user", "content": "Write a short story about AI"}
+ ],
+ "stream": true
+ }'
+ ```
+
-
- 使用 temperature、max tokens 等参数控制模型的响应方式：
+ 通过 temperature、max tokens 等参数控制模型的响应方式：
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.environ.get("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- completion = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[
- {"role": "system", "content": "You are a creative storyteller"},
- {"role": "user", "content": "Tell me a creative story"}
- ],
- temperature=0.8,
- max_tokens=500,
- top_p=0.9,
- frequency_penalty=0.5,
- presence_penalty=0.5,
- extra_body={
- "venice_parameters": {
- "include_venice_system_prompt": False
- }
- }
- )
-
- print(completion.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const completion = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [
- { role: 'system', content: 'You are a creative storyteller' },
- { role: 'user', content: 'Tell me a creative story' }
- ],
- temperature: 0.8,
- max_tokens: 500,
- top_p: 0.9,
- frequency_penalty: 0.5,
- presence_penalty: 0.5,
- venice_parameters: {
- include_venice_system_prompt: false
- }
- });
-
- console.log(completion.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
+
+ ```python Python
+ import os
+ from openai import OpenAI
+
+ client = OpenAI(
+ api_key=os.environ.get("VENICE_API_KEY"),
+ base_url="https://api.venice.ai/api/v1"
+ )
+
+ completion = client.chat.completions.create(
+ model="zai-org-glm-5",
+ messages=[
{"role": "system", "content": "You are a creative storyteller"},
{"role": "user", "content": "Tell me a creative story"}
- ],
- "temperature": 0.8,
- "max_tokens": 500,
- "top_p": 0.9,
- "frequency_penalty": 0.5,
- "presence_penalty": 0.5,
- "stream": false,
- "venice_parameters": {
- "include_venice_system_prompt": false
- }
- }'
- ```
-
-
- 有关所有支持参数的更多信息，请查看 [Chat Completions 文档](/api-reference/endpoint/chat/completions)。
-
-
-
----
-
-## 更多能力
-
-### 图像生成
-
-使用扩散模型从文本 prompt 创建图像：
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/image/generate"
-
- payload = {
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024,
- "format": "webp"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/image/generate';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'venice-sd35',
- prompt: 'A cyberpunk city with neon lights and rain',
- width: 1024,
- height: 1024,
- format: 'webp'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/image/generate \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "venice-sd35",
- "prompt": "A cyberpunk city with neon lights and rain",
- "width": 1024,
- "height": 1024
- }'
- ```
-
-
-**注意：** 响应在 `images` 数组中返回 base64 编码的图像。解码 base64 字符串以保存或显示图像。
-
-**热门图像模型：**
-- `qwen-image` - 最高质量的图像生成
-- `venice-sd35` - 默认选择，适用于所有功能
-- `hidream` - 用于生产用途的快速生成
-
-
- 查看所有可用图像模型及其定价和能力
-
-
-要了解更高级的参数选项，如 `cfg_scale`、`negative_prompt`、`style_preset`、`seed`、`variants` 等，请查看 [图像 API 参考](/api-reference/endpoint/image/generate)。
-
-### 图像编辑
-
-使用 Qwen-Image 模型通过 AI 驱动的修复修改现有图像：
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/edit"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "prompt": "Colorize",
- "image": image_base64
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("edited_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- prompt: 'Colorize',
- image: imageBase64
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/edit', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('edited_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/edit \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "prompt": "Colorize",
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A..."
- }'
- ```
-
-
-**注意：** 图像编辑器使用 Qwen-Image 模型，是一个实验性端点。将输入图像作为 base64 编码字符串发送，API 以二进制数据返回编辑后的图像。
-
-有关所有参数，请参阅 [Image Edit API](/api-reference/endpoint/image/edit)。
-
-### 图像放大
-
-将图像增强并放大到更高分辨率：
-
-
- ```python Python
- import os
- import requests
- import base64
-
- url = "https://api.venice.ai/api/v1/image/upscale"
-
- with open("image.jpg", "rb") as f:
- image_base64 = base64.b64encode(f.read()).decode('utf-8')
-
- payload = {
- "image": image_base64,
- "scale": 2
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- with open("upscaled_image.png", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const imageBuffer = fs.readFileSync('image.jpg');
- const imageBase64 = imageBuffer.toString('base64');
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- image: imageBase64,
- scale: 2
- })
- };
-
- const response = await fetch('https://api.venice.ai/api/v1/image/upscale', options);
- const imageData = await response.arrayBuffer();
- fs.writeFileSync('upscaled_image.png', Buffer.from(imageData));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/image/upscale \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...",
- "scale": 2
- }'
- ```
-
-
-**注意：** 将输入图像作为 base64 编码字符串发送，API 以二进制数据返回放大的图像。
-
-有关所有参数，请参阅 [Image Upscale API](/api-reference/endpoint/image/upscale)。
-
-### 文本转语音
-
-使用 50+ 种多语言声音将文本转换为音频：
-
-
- ```python Python
- import os
- import requests
-
- response = requests.post(
- "https://api.venice.ai/api/v1/audio/speech",
- headers={
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- },
- json={
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }
- )
-
- with open("speech.mp3", "wb") as f:
- f.write(response.content)
- ```
-
- ```javascript Node.js
- import fs from 'fs';
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/speech', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- input: 'Hello, welcome to Venice Voice.',
- model: 'tts-kokoro',
- voice: 'af_sky'
- })
- });
-
- const audioBuffer = await response.arrayBuffer();
- fs.writeFileSync('speech.mp3', Buffer.from(audioBuffer));
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/speech \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "input": "Hello, welcome to Venice Voice.",
- "model": "tts-kokoro",
- "voice": "af_sky"
- }' \
- --output speech.mp3
- ```
-
-
-`tts-kokoro` 模型支持 50+ 种多语言声音，包括 `af_sky`、`af_nova`、`am_liam`、`bf_emma`、`zf_xiaobei` 和 `jm_kumo`。
-
-有关所有声音选项，请参阅 [TTS API](/api-reference/endpoint/audio/speech)。
-
-### 语音转文本
-
-将音频文件转录为文本：
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/audio/transcriptions"
-
- with open("audio.mp3", "rb") as f:
- response = requests.post(
- url,
- headers={"Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}"},
- files={"file": f},
- data={
- "model": "nvidia/parakeet-tdt-0.6b-v3",
- "response_format": "json"
- }
- )
-
- print(response.json())
- ```
-
- ```javascript Node.js
- import fs from 'fs';
- import FormData from 'form-data';
-
- const form = new FormData();
- form.append('file', fs.createReadStream('audio.mp3'));
- form.append('model', 'nvidia/parakeet-tdt-0.6b-v3');
- form.append('response_format', 'json');
-
- const response = await fetch('https://api.venice.ai/api/v1/audio/transcriptions', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- ...form.getHeaders()
- },
- body: form
- });
-
- const data = await response.json();
- console.log(data);
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/audio/transcriptions \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --form file=@audio.mp3 \
- --form model=nvidia/parakeet-tdt-0.6b-v3 \
- --form response_format=json
- ```
-
-
-支持的格式：WAV、FLAC、MP3、M4A、AAC、MP4。启用 `timestamps=true` 以获取字级时间数据。
-
-有关所有选项，请参阅 [Transcriptions API](/api-reference/endpoint/audio/transcriptions)。
-
-### Embeddings
-
-为语义搜索、RAG 和推荐生成向量嵌入：
-
-
- ```python Python
- import os
- import requests
-
- url = "https://api.venice.ai/api/v1/embeddings"
-
- payload = {
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }
-
- headers = {
- "Authorization": f"Bearer {os.getenv('VENICE_API_KEY')}",
- "Content-Type": "application/json"
- }
-
- response = requests.post(url, json=payload, headers=headers)
-
- print(response.json())
- ```
-
- ```javascript Node.js
- const url = 'https://api.venice.ai/api/v1/embeddings';
-
- const options = {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.VENICE_API_KEY}`,
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- model: 'text-embedding-bge-m3',
- input: 'Privacy-first AI infrastructure for semantic search',
- encoding_format: 'float'
- })
- };
-
- try {
- const response = await fetch(url, options);
- const data = await response.json();
- console.log(data);
- } catch (error) {
- console.error(error);
- }
- ```
-
- ```bash cURL
- curl --request POST \
- --url https://api.venice.ai/api/v1/embeddings \
- --header "Authorization: Bearer $VENICE_API_KEY" \
- --header "Content-Type: application/json" \
- --data '{
- "model": "text-embedding-bge-m3",
- "input": "Privacy-first AI infrastructure for semantic search",
- "encoding_format": "float"
- }'
- ```
-
-
-有关批处理和高级选项，请参阅 [Embeddings API](/api-reference/endpoint/embeddings/generate)。
-
-### Vision（多模态）
-
-使用支持视觉的模型如 `qwen3-vl-235b-a22b` 与文本一起分析图像：
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- response = client.chat.completions.create(
- model="qwen3-vl-235b-a22b",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What is in this image?"},
- {
- "type": "image_url",
- "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
- }
- ]
- }
- ]
- )
-
- print(response.choices[0].message.content)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const response = await client.chat.completions.create({
- model: 'qwen3-vl-235b-a22b',
- messages: [
- {
- role: 'user',
- content: [
- { type: 'text', text: 'What is in this image?' },
- {
- type: 'image_url',
- image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' }
- }
- ]
- }
- ]
- });
-
- console.log(response.choices[0].message.content);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "qwen3-vl-235b-a22b",
- "messages": [
- {
- "role": "user",
- "content": [
- {
- "type": "text",
- "text": "What is in this image?"
- },
- {
- "type": "image_url",
- "image_url": {
- "url": "https://www.gstatic.com/webp/gallery/1.jpg"
- }
+ ],
+ temperature=0.8,
+ max_tokens=500,
+ top_p=0.9,
+ frequency_penalty=0.5,
+ presence_penalty=0.5,
+ extra_body={
+ "venice_parameters": {
+ "include_venice_system_prompt": False
}
- ]
}
- ]
- }'
- ```
-
-
-### 函数调用
-
-定义模型可以调用以与外部工具和 API 交互的函数：
-
-
- ```python Python
- import os
- from openai import OpenAI
-
- client = OpenAI(
- api_key=os.getenv("VENICE_API_KEY"),
- base_url="https://api.venice.ai/api/v1"
- )
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
- }
- ]
-
- response = client.chat.completions.create(
- model="zai-org-glm-5",
- messages=[{"role": "user", "content": "What's the weather in San Francisco?"}],
- tools=tools
- )
-
- print(response.choices[0].message)
- ```
-
- ```javascript Node.js
- import OpenAI from 'openai';
-
- const client = new OpenAI({
- apiKey: process.env.VENICE_API_KEY,
- baseURL: 'https://api.venice.ai/api/v1'
- });
-
- const tools = [
- {
- type: 'function',
- function: {
- name: 'get_weather',
- description: 'Get the current weather in a location',
- parameters: {
- type: 'object',
- properties: {
- location: {
- type: 'string',
- description: 'The city and state'
- }
- },
- required: ['location']
- }
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: 'zai-org-glm-5',
- messages: [{ role: 'user', content: "What's the weather in San Francisco?" }],
- tools: tools
- });
-
- console.log(response.choices[0].message);
- ```
-
- ```bash cURL
- curl https://api.venice.ai/api/v1/chat/completions \
- -H "Authorization: Bearer $VENICE_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "model": "zai-org-glm-5",
- "messages": [
- {
- "role": "user",
- "content": "What'\''s the weather in San Francisco?"
+ )
+
+ print(completion.choices[0].message.content)
+ ```
+
+ ```javascript Node.js
+ import OpenAI from 'openai';
+
+ const client = new OpenAI({
+ apiKey: process.env.VENICE_API_KEY,
+ baseURL: 'https://api.venice.ai/api/v1'
+ });
+
+ const completion = await client.chat.completions.create({
+ model: 'zai-org-glm-5',
+ messages: [
+ { role: 'system', content: 'You are a creative storyteller' },
+ { role: 'user', content: 'Tell me a creative story' }
+ ],
+ temperature: 0.8,
+ max_tokens: 500,
+ top_p: 0.9,
+ frequency_penalty: 0.5,
+ presence_penalty: 0.5,
+ venice_parameters: {
+ include_venice_system_prompt: false
}
- ],
- "tools": [
- {
- "type": "function",
- "function": {
- "name": "get_weather",
- "description": "Get the current weather in a location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state"
- }
- },
- "required": ["location"]
- }
- }
+ });
+
+ console.log(completion.choices[0].message.content);
+ ```
+
+ ```bash cURL
+ curl https://api.venice.ai/api/v1/chat/completions \
+ -H "Authorization: Bearer $VENICE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "zai-org-glm-5",
+ "messages": [
+ {"role": "system", "content": "You are a creative storyteller"},
+ {"role": "user", "content": "Tell me a creative story"}
+ ],
+ "temperature": 0.8,
+ "max_tokens": 500,
+ "top_p": 0.9,
+ "frequency_penalty": 0.5,
+ "presence_penalty": 0.5,
+ "stream": false,
+ "venice_parameters": {
+ "include_venice_system_prompt": false
}
- ]
- }'
- ```
-
+ }'
+ ```
+
+
+
+ 请查阅 [聊天补全文档](/api-reference/endpoint/chat/completions) 了解所有受支持参数的更多信息。
+
+
---
-## 下一步
+## 后续步骤
-既然您已经发出了第一个请求，请进一步探索 Venice API 提供的更多内容：
+在完成首个请求之后，您可以进一步探索 Venice API 提供的更多功能：
- 比较所有可用模型及其能力、定价和上下文限制
+ 比较所有可用模型的能力、价格和上下文限制
+
- 探索包含所有端点和参数的详细 API 文档
+ 浏览详细的 API 文档，包含所有端点和参数
+
- 了解如何获取具有保证 schema 的 JSON 响应
+ 学习如何获得具有确定 schema 的 JSON 响应
+
- 使用 agent 应用、编码 agent、MCP 工具、skill 和加密货币工作流进行构建
+ 使用 agent 应用、编码 agent、MCP 工具、技能和加密工作流进行构建
-### 其他资源
+### 更多资源
- 了解速率限制和生产使用的最佳实践
+ 了解速率限制及生产环境使用的最佳实践
+
- 处理 API 错误和故障排查的参考
+ 处理 API 错误和排查问题的参考
-
- 导入我们的完整 Postman collection 以方便测试
+
+
+ 导入我们完整的 Postman 集合，轻松进行测试
+
- 了解 Venice 的隐私优先架构和数据处理
+ 了解 Venice 隐私优先的架构与数据处理方式
@@ -998,9 +389,9 @@ description: "Venice API 快速上手 —— 生成 API 密钥、发送您的第
## 需要帮助？
-- **Discord 社区**：加入我们的 [Discord 服务器](https://discord.gg/askvenice) 获取支持和讨论
-- **文档**：浏览我们的 [完整 API 参考](/api-reference/api-spec)
-- **状态页**：在 [veniceai-status.com](https://veniceai-status.com) 检查服务状态
-- **Twitter**：关注 [@AskVenice](https://x.com/AskVenice) 获取更新
+- **Discord 社区**：加入我们的 [Discord 服务器](https://discord.gg/askvenice) 获取支持并参与讨论
+- **文档**：浏览我们的[完整 API 参考](/api-reference/api-spec)
+- **状态页面**：在 [veniceai-status.com](https://veniceai-status.com) 查看服务状态
+- **Twitter**：关注 [@AskVenice](https://x.com/AskVenice) 获取最新动态