← All models
Qwen · Language model
Qwen3 30B A3B Thinking 2507
qwen/qwen3-30b-a3b-thinking-2507- Language
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Specifications
- Context window
- 81,920 tokens
- Max output
- 32,768 tokens
- Input
- text
- Output
- text
- Reasoning
- always on
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-06-30
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- max_tokens
- presence_penalty
- reasoning
- response_format
- seed
- stop
- temperature
- tool_choice
- tools
- top_k
- 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/qwen3-30b-a3b-thinking-2507","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'