feat(together-ai/Qwen/Qwen3.5-35B-A3B-Lora): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for together-ai/Qwen/Qwen3.5-35B-A3B-Lora.

---

Note

Low Risk
Single auto-generated YAML catalog addition with no application logic or runtime behavior changes.

Overview
Adds a new Together AI provider definition for Qwen/Qwen3.5-35B-A3B-Lora, registering it as a provisioned chat model with a 262144 token context window and $0 input/output token costs (aligned with fine-tuned / LoRA deployment docs).

The entry is minimal compared to the existing Qwen/Qwen3.5-35B-A3B catalog file: no modalities, output limits, or status field—only chat mode and a fine-tuning documentation source.

^{Reviewed by Cursor Bugbot for commit 1aeccc7. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 2
• Passed: 0
• Failed: 2
• Validation failed: 0
• Errored: 0
• Skipped: 0
• Success rate: 0.0%

Provider	Model	Scenarios
together-ai	Qwen/Qwen3.5-35B-A3B-Lora	failure: params:stream, params

Failures (2)

together-ai/Qwen/Qwen3.5-35B-A3B-Lora — params:stream (failure)

Error

Traceback (most recent call last):
  File "/tmp/tmpymtrun8o/snippet.py", line 5, in <module>
    response = client.chat.completions.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_utils/_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'status': 'failure', 'message': 'together-ai error: Unable to access non-serverless model Qwen/Qwen3.5-35B-A3B-Lora. Please visit https://api.together.ai/models/Qwen/Qwen3.5-35B-A3B-Lora to create and start a new dedicated endpoint for the model.', 'error': {'message': 'together-ai error: Unable to access non-serverless model Qwen/Qwen3.5-35B-A3B-Lora. Please visit https://api.together.ai/models/Qwen/Qwen3.5-35B-A3B-Lora to create and start a new dedicated endpoint for the model.', 'type': 'APIError', 'code': '400'}, 'error_origin_level': 'api_error', 'provider': 'together-ai'}

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-together-ai/Qwen-Qwen3.5-35B-A3B-Lora",
    messages=[
        {"role": "user", "content": "What is the capital of France?"},
    ],
    stream=True,
)

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)

together-ai/Qwen/Qwen3.5-35B-A3B-Lora — params (failure)

Error

Traceback (most recent call last):
  File "/tmp/tmp_m9xq1r7/snippet.py", line 5, in <module>
    response = client.chat.completions.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_utils/_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'status': 'failure', 'message': 'together-ai error: Unable to access non-serverless model Qwen/Qwen3.5-35B-A3B-Lora. Please visit https://api.together.ai/models/Qwen/Qwen3.5-35B-A3B-Lora to create and start a new dedicated endpoint for the model.', 'error': {'message': 'together-ai error: Unable to access non-serverless model Qwen/Qwen3.5-35B-A3B-Lora. Please visit https://api.together.ai/models/Qwen/Qwen3.5-35B-A3B-Lora to create and start a new dedicated endpoint for the model.', 'type': 'APIError', 'code': '400'}, 'error_origin_level': 'api_error', 'provider': 'together-ai'}

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-together-ai/Qwen-Qwen3.5-35B-A3B-Lora",
    messages=[
        {"role": "user", "content": "What is the capital of France?"},
    ],
    stream=False,
)

print(response.choices[0].message.content)

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 1
• Passed: 0
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 1
• Success rate: 0.0%

Provider	Model	Scenarios
together-ai	Qwen/Qwen3.5-35B-A3B-Lora	skipped: skip-check

Skipped (1)

together-ai/Qwen/Qwen3.5-35B-A3B-Lora — skip-check (skipped)

Skip reason

Provisioned model

[cursor]

Cursor Bugbot has reviewed your changes and found 2 potential issues.

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

^{Reviewed by Cursor Bugbot for commit 1aeccc7. Configure here.}