---
id: "qwen/qwen3-coder"
also: ["qwen/qwen3-coder-480b-a35b-07-25", "Qwen/Qwen3-Coder-480B-A35B-Instruct", "hf/Qwen/Qwen3-Coder-480B-A35B-Instruct", "vercel/alibaba/qwen3-coder"]
cheapest_list_usd_per_m: "0.22 in, 1.8 out, at google-vertex/us-south1 on openrouter"
cheapest_effective_usd_per_m: "0.0609 in, 1.8 out, at vertex on vercel"
context: 262144
max_output: 65536
input: ["text"]
output: ["text"]
released: "2025-07-23"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["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"]
endpoints: 11
gateways: "openrouter (5), vercel (4), hf (2)"
no_training: 8
trains: 0
retains_prompts: 1
---
# Qwen: Qwen3 Coder 480B A35B

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...