feat(openrouter): add new models [bot]

[harshiv-26]

Auto-generated by model-addition-agent for provider openrouter.

---

Note

Low Risk
Low risk: this PR only adds new OpenRouter model metadata/config YAMLs (costs, limits, features) without changing runtime logic.

Overview
Adds eight new OpenRouter model definition YAMLs, expanding the catalog with IBM Granite, InclusionAI Ling, Mistral Medium 3.5, NVIDIA Nemotron (free), OpenRouter Owl Alpha, Poolside Laguna (free variants), and xAI Grok 4.3.

Each model file specifies pricing, supported features (e.g., function_calling, tool_choice, structured_output/prompt_caching where applicable), modalities, and token/context limits; some also include default sampling params and thinking support.

^{Reviewed by Cursor Bugbot for commit 4402292. Bugbot is set up for automated code reviews on this repo. Configure here.}

[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 83be96f. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 47
• Passed: 42
• Failed: 0
• Validation failed: 1
• Errored: 0
• Skipped: 4
• Success rate: 97.67%

Provider	Model	Scenarios
openrouter	ibm-granite/granite-4.1-8b	success: tool-call:text-text, params:text-text, params:text-text:stream, tool-call:text-text:stream, json-output:text-text:stream, structured-output:text-text:stream, json-output:text-text, structured-output:text-text
openrouter	inclusionai/ling-2.6-flash	success: json-output:text-text, json-output:text-text:stream, params:text-text, params:text-text:stream, tool-call:text-text:stream, structured-output:text-text:stream, structured-output:text-text, tool-call:text-text
openrouter	mistralai/mistral-medium-3-5	success: structured-output:text-text:stream, tool-call:text-text:stream, tool-call:text-text, json-output:text-text:stream, structured-output:text-text, json-output:text-text, params:text-text, params:text-text:stream, reasoning:text-text:stream, reasoning:text-text
openrouter	nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free	skipped: skip-check
openrouter	openrouter/owl-alpha	success: structured-output:text-text:stream, structured-output:text-text, json-output:text-text:stream, json-output:text-text, params:text-text, params:text-text:stream validation_failure: tool-call:text-text:stream skipped: tool-call:text-text
openrouter	poolside/laguna-m.1:free	skipped: skip-check
openrouter	poolside/laguna-xs.2:free	skipped: skip-check
openrouter	x-ai/grok-4.3	success: tool-call:text-text:stream, params:text-text, params:text-text:stream, tool-call:text-text, structured-output:text-text, structured-output:text-text:stream, json-output:text-text:stream, json-output:text-text, reasoning:text-text:stream, reasoning:text-text

Failures (1)

openrouter/openrouter/owl-alpha — tool-call:text-text:stream (validation_failure)

Error:

Traceback (most recent call last):
  File "/tmp/tmpzhy8kgfi/snippet.py", line 50, in <module>
    raise Exception("VALIDATION FAILED: tool-call stream - no tool calls received")
Exception: VALIDATION FAILED: tool-call stream - no tool calls received

Code snippet

from openai import OpenAI

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

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location.",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city name, e.g. London",
                    },
                },
                "required": ["location"],
                "additionalProperties": False,
            },
            "strict": True,
        },
    },
]

response = client.chat.completions.create(
    model="test-v2-openrouter/openrouter-owl-alpha",
    messages=[
        {"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
    ],
    tools=tools,
    tool_choice="auto",
    stream=True,
)

_tool_calls_made = 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 delta.tool_calls:
            _tool_calls_made = True
            for _tc in delta.tool_calls:
                if _tc.function:
                    print(_tc.function.arguments or "", end="", flush=True)

if not _tool_calls_made:
    raise Exception("VALIDATION FAILED: tool-call stream - no tool calls received")
print("\nVALIDATION: tool-call stream SUCCESS")

Skipped (4)

openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — skip-check (skipped)

Skip reason:

Paid version tested, skipping the free version due to rate limits

openrouter/poolside/laguna-m.1:free — skip-check (skipped)

Skip reason:

Paid version tested, skipping the free version due to rate limits

openrouter/poolside/laguna-xs.2:free — skip-check (skipped)

Skip reason:

Paid version tested, skipping the free version due to rate limits

openrouter/openrouter/owl-alpha — tool-call:text-text (skipped)

Skip reason:

Snippet runner exceeded its timeout