<!-- generated by scripts/fetch-models.ts from GET /v1/models. do not edit. -->

# qwen/qwen3.5-35b-a3b

Purpose: Agent-readable model facts.
Last updated: 2026-10-02

Mixture-of-experts text and vision-language model for coding, agentic tasks, and multimodal reasoning.

## Capabilities

| Field | Value |
| --- | --- |
| Model ID | `qwen/qwen3.5-35b-a3b` |
| Input modalities | Text, Image, Video |
| Output modalities | Text |
| Endpoints | `/v1/chat/completions` |
| Supported parameters | `temperature`, `top_p`, `top_k`, `min_p`, `frequency_penalty`, `presence_penalty`, `repetition_penalty`, `max_tokens`, `logit_bias`, `logprobs`, `top_logprobs`, `seed`, `response_format`, `structured_outputs`, `stop`, `tools`, `tool_choice`, `parallel_tool_calls`, `include_reasoning`, `reasoning_effort` |

## Related links

- [Model catalog](https://sprag.ai/models/index.md)
- [Pricing](https://sprag.ai/pricing)