← All models
Qwen · Language model
Qwen3 VL 8B Thinking
qwen/qwen3-vl-8b-thinking- Language
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
Specifications
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- Input
- image, text
- Output
- text
- Reasoning
- always on
- Tokenizer
- Qwen3
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logprobs
- max_tokens
- presence_penalty
- reasoning
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3-vl-8b-thinking","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'