feat(openrouter/tencent/hy3): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/tencent/hy3.

---

Note

Low Risk
Declarative catalog-only change with no runtime or auth logic; low blast radius unless metadata (costs/limits) is wrong.

Overview
Adds a new OpenRouter provider definition for tencent/hy3, registering the model for chat routing with token pricing (including cache-read input), a 262K context window, and 131K max output tokens.

The entry marks thinking, function calling, prompt caching, and tool choice as supported, with default temperature / top_p params and a link to the OpenRouter model page as the source.

^{Reviewed by Cursor Bugbot for commit ccb0fe6. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 8
• Passed: 8
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 0
• Success rate: 100.0%

Provider	Model	Scenarios
openrouter	tencent/hy3	success: params:text-text, params:text-text:stream, tool-call:text-text, structured-output:text-text:stream, tool-call:text-text:stream, structured-output:text-text, reasoning:text-text:stream, reasoning:text-text

Successes (8)

openrouter/tencent/hy3 — params:text-text (success)

Output

The capital of France is Paris.

openrouter/tencent/hy3 — params:text-text:stream (success)

Output

The capital of France is Paris.

openrouter/tencent/hy3 — tool-call:text-text (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

openrouter/tencent/hy3 — structured-output:text-text:stream (success)

Output

{
  "name": "science fair",
  "date": "Friday",
  "participants": ["Alice", "Bob"]
}
VALIDATION: structured-output stream SUCCESS

openrouter/tencent/hy3 — tool-call:text-text:stream (success)

Output

{"location": "London"}
VALIDATION: tool-call stream SUCCESS

openrouter/tencent/hy3 — structured-output:text-text (success)

Output

{
  "name": "science fair",
  "date": "Friday",
  "participants": ["Alice", "Bob"]
}
VALIDATION: structured-output SUCCESS

openrouter/tencent/hy3 — reasoning:text-text:stream (success)

Output

To evaluate \(3^{3^{3^{3}}}\), we must respect the **standard convention for exponentiation**: it is **right-associative**. That means

\[
a^{b^{c^{d}
... (truncated, 2500 chars omitted)

openrouter/tencent/hy3 — reasoning:text-text (success)

Output

To evaluate \(3^{3^{3^{3}}}\), we must be careful about **how exponentiation groups**. 

### Step 1: Understand the associativity of exponentiation
Ex
... (truncated, 2449 chars omitted)

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 6
• Passed: 4
• Failed: 0
• Validation failed: 1
• Errored: 0
• Skipped: 1
• Success rate: 80.0%

Provider	Model	Scenarios
openrouter	tencent/hy3	success: params:text-text:stream, tool-call:text-text, params:text-text, reasoning:text-text:stream validation_failure: tool-call:text-text:stream skipped: reasoning:text-text

Failures (1)

openrouter/tencent/hy3 — tool-call:text-text:stream (validation_failure)

Error

Traceback (most recent call last):
  File "/tmp/tmpx81szow3/snippet.py", line 49, 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/tencent-hy3",
    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")

Successes (4)

openrouter/tencent/hy3 — params:text-text:stream (success)

Output

The capital of France is Paris.

openrouter/tencent/hy3 — tool-call:text-text (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

openrouter/tencent/hy3 — params:text-text (success)

Output

The capital of France is Paris.

openrouter/tencent/hy3 — reasoning:text-text:stream (success)

Output

To calculate \(3^{3^{3^{3}}}\), we must follow the standard mathematical convention for exponentiation and then simplify step by step.

---

### Step 
... (truncated, 2092 chars omitted)

Skipped (1)

openrouter/tencent/hy3 — reasoning:text-text (skipped)

Skip reason

Upstream rate limited the request