From 56e8fcc5797271cc3ce0f0400fcea4ca63dac4d6 Mon Sep 17 00:00:00 2001
From: Guillaume Gay <guillaume.gay@protonmail.com>
Date: Tue, 26 May 2026 09:49:13 +0200
Subject: [PATCH] feat: add Google Gemini subscription parameters

---
 .../gemini-2.5-flash-lite-subscription.yaml   | 67 +++++++++++++++++
 .../google/gemini-2.5-flash-subscription.yaml | 70 ++++++++++++++++++
 .../google/gemini-2.5-pro-subscription.yaml   | 69 ++++++++++++++++++
 .../gemini-3-flash-preview-subscription.yaml  | 72 +++++++++++++++++++
 ...i-3.1-flash-lite-preview-subscription.yaml | 72 +++++++++++++++++++
 .../gemini-3.1-flash-lite-subscription.yaml   | 72 +++++++++++++++++++
 .../gemini-3.1-pro-preview-subscription.yaml  | 70 ++++++++++++++++++
 7 files changed, 492 insertions(+)
 create mode 100644 models/google/gemini-2.5-flash-lite-subscription.yaml
 create mode 100644 models/google/gemini-2.5-flash-subscription.yaml
 create mode 100644 models/google/gemini-2.5-pro-subscription.yaml
 create mode 100644 models/google/gemini-3-flash-preview-subscription.yaml
 create mode 100644 models/google/gemini-3.1-flash-lite-preview-subscription.yaml
 create mode 100644 models/google/gemini-3.1-flash-lite-subscription.yaml
 create mode 100644 models/google/gemini-3.1-pro-preview-subscription.yaml

diff --git a/models/google/gemini-2.5-flash-lite-subscription.yaml b/models/google/gemini-2.5-flash-lite-subscription.yaml
new file mode 100644
index 0000000..61ff681
--- /dev/null
+++ b/models/google/gemini-2.5-flash-lite-subscription.yaml
@@ -0,0 +1,67 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-2.5-flash-lite
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingBudget
+    type: integer
+    label: Thinking budget
+    description: Number of thinking tokens Gemini should use; -1 uses dynamic thinking, 0 disables thinking, and fixed budgets start at 512 tokens.
+    default: 0
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-2.5-flash-subscription.yaml b/models/google/gemini-2.5-flash-subscription.yaml
new file mode 100644
index 0000000..bdc93c1
--- /dev/null
+++ b/models/google/gemini-2.5-flash-subscription.yaml
@@ -0,0 +1,70 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-2.5-flash
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingBudget
+    type: integer
+    label: Thinking budget
+    description: Number of thinking tokens Gemini should use; 0 disables thinking and -1 uses dynamic thinking.
+    default: -1
+    range:
+      min: -1
+      max: 24576
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-2.5-pro-subscription.yaml b/models/google/gemini-2.5-pro-subscription.yaml
new file mode 100644
index 0000000..58273f9
--- /dev/null
+++ b/models/google/gemini-2.5-pro-subscription.yaml
@@ -0,0 +1,69 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-2.5-pro
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingBudget
+    type: integer
+    label: Thinking budget
+    description: Maximum number of thinking tokens Gemini should use before producing the final answer.
+    range:
+      min: 128
+      max: 32768
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-3-flash-preview-subscription.yaml b/models/google/gemini-3-flash-preview-subscription.yaml
new file mode 100644
index 0000000..daba365
--- /dev/null
+++ b/models/google/gemini-3-flash-preview-subscription.yaml
@@ -0,0 +1,72 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-3-flash-preview
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingLevel
+    type: enum
+    label: Thinking level
+    description: Controls Gemini 3 Flash reasoning effort.
+    default: high
+    values:
+      - minimal
+      - low
+      - medium
+      - high
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-3.1-flash-lite-preview-subscription.yaml b/models/google/gemini-3.1-flash-lite-preview-subscription.yaml
new file mode 100644
index 0000000..414eb90
--- /dev/null
+++ b/models/google/gemini-3.1-flash-lite-preview-subscription.yaml
@@ -0,0 +1,72 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-3.1-flash-lite-preview
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingLevel
+    type: enum
+    label: Thinking level
+    description: Controls Gemini 3.1 Flash-Lite reasoning effort.
+    default: high
+    values:
+      - minimal
+      - low
+      - medium
+      - high
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-3.1-flash-lite-subscription.yaml b/models/google/gemini-3.1-flash-lite-subscription.yaml
new file mode 100644
index 0000000..fafc168
--- /dev/null
+++ b/models/google/gemini-3.1-flash-lite-subscription.yaml
@@ -0,0 +1,72 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-3.1-flash-lite
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingLevel
+    type: enum
+    label: Thinking level
+    description: Controls Gemini 3.1 Flash-Lite reasoning effort.
+    default: high
+    values:
+      - minimal
+      - low
+      - medium
+      - high
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format
diff --git a/models/google/gemini-3.1-pro-preview-subscription.yaml b/models/google/gemini-3.1-pro-preview-subscription.yaml
new file mode 100644
index 0000000..32d1adf
--- /dev/null
+++ b/models/google/gemini-3.1-pro-preview-subscription.yaml
@@ -0,0 +1,70 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: subscription
+model: gemini-3.1-pro-preview
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingLevel
+    type: enum
+    label: Thinking level
+    description: Controls Gemini 3 Pro reasoning effort.
+    default: high
+    values:
+      - low
+      - high
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format