feat(google-gemini): update model YAMLs [bot]

[harshiv-26]

Auto-generated by poc-agent for provider google-gemini.

---

Note

Medium Risk
Medium risk because it changes model configuration used for pricing calculations and enforces a significantly smaller context_window/max_input_tokens for gemini-robotics-er-1.6-preview, which could impact workloads relying on prior limits.

Overview
Updates Google Gemini model metadata YAMLs.

Adds batched input pricing (input_cost_per_token_batches) to gemini-3.1-flash-tts-preview.

Reduces gemini-robotics-er-1.6-preview limits by lowering context_window and max_input_tokens from 1048576 to 131072.

^{Reviewed by Cursor Bugbot for commit 619d9b9. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 17
• Passed: 15
• Failed: 0
• Validation failed: 2
• Errored: 0
• Skipped: 0
• Success rate: 88.24%

Provider	Model	Scenarios
google-gemini	gemini-3.1-flash-tts-preview	success: params
google-gemini	gemini-robotics-er-1.6-preview	success: tool-call, params, tool-call:stream, structured-output:stream, tool-call:stream:google-genai, params:stream, tool-call:google-genai, params:google-genai, params:stream:google-genai, structured-output:stream:google-genai, structured-output, structured-output:google-genai, reasoning:stream:google-genai, reasoning:google-genai validation_failure: reasoning, reasoning:stream

Failures (2)

google-gemini/gemini-robotics-er-1.6-preview — reasoning (validation_failure)

Error:

Traceback (most recent call last):
  File "/tmp/tmpa5o9yuyh/snippet.py", line 42, in <module>
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
Exception: VALIDATION FAILED: reasoning - no reasoning information in response

Code snippet

from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-gemini/gemini-robotics-er-1.6-preview",
    messages=[
        {"role": "user", "content": "Hi"},
        {"role": "assistant", "content": "Hi, how can I help you"},
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=False,
)

_usage = getattr(response, "usage", None)
_reasoning_detected = False

_choices = getattr(response, "choices", None)
if _choices and len(_choices) > 0:
    _message = getattr(_choices[0], "message", None)
else:
    _message = None

if _message and getattr(_message, "content", None) is not None:
    print(_message.content)

if _usage is not None:
    _output_token_details = getattr(_usage, "completion_tokens_details", None)
    if _output_token_details and getattr(_output_token_details, "reasoning_tokens", 0) > 0:
        _reasoning_detected = True
    elif getattr(_usage, "reasoning", None) is not None:
        _reasoning_detected = True

if getattr(_message, "reasoning_content", None) is not None:
    _reasoning_detected = True
elif getattr(_message, "reasoning", None) is not None:
    _reasoning_detected = True

if not _reasoning_detected:
    print("Response: ", response)
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
print("VALIDATION: reasoning SUCCESS")

google-gemini/gemini-robotics-er-1.6-preview — reasoning:stream (validation_failure)

Error:

Traceback (most recent call last):
  File "/tmp/tmpxz5clhg2/snippet.py", line 34, in <module>
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
Exception: VALIDATION FAILED: reasoning stream - no reasoning information in stream

Code snippet

from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-gemini/gemini-robotics-er-1.6-preview",
    messages=[
        {"role": "user", "content": "Hi"},
        {"role": "assistant", "content": "Hi, how can I help you"},
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=True,
)

_reasoning_detected = False
for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta
        if delta.content is not None:
            print(delta.content, end="", flush=True)
        if getattr(delta, "reasoning_content", None) is not None:
            _reasoning_detected = True
        if getattr(delta, "reasoning", None) is not None:
            _reasoning_detected = True

    _usage = getattr(chunk, "usage", None)
    if _usage is not None:
        _details = getattr(_usage, "completion_tokens_details", None)
        if _details and getattr(_details, "reasoning_tokens", 0) > 0:
            _reasoning_detected = True

if not _reasoning_detected:
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning stream SUCCESS")

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 619d9b9. Configure here.}

[cursor]

Missing output batch cost in TTS model pricing

Medium Severity

Adding input_cost_per_token_batches without a corresponding output_cost_per_token_batches is inconsistent with the other TTS models. Both gemini-2.5-pro-preview-tts.yaml (which has identical per-token pricing) and gemini-2.5-flash-preview-tts.yaml include output_cost_per_token_batches at a 50% discount of their output_cost_per_audio_token. This model's output_cost_per_audio_token is 0.00002, so the expected batch output cost would be 0.00001.

 

^{Reviewed by Cursor Bugbot for commit 619d9b9. Configure here.}