← All models
Qwen · Language model
Qwen3 Coder 480B A35B
qwen/qwen3-coder- Language
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Specifications
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text
- Output
- text
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-06-30
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- repetition_penalty
- 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-coder","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'