Qwen3-Coder-480B: Pricing, Context, and Benchmarks

Qwen3-Coder-480B is Alibaba's Qwen3 model released on 2025-07-22. It runs on a 1.0M-token context window, priced at $2.00/M input and $6.00/M output. Code-specialized 480B MoE. 1M context. Comparable to Sonnet on coding agents at lower cost.

Specifications

Benchmark scores

Scores reflect single measurements on the date shown. Reproducibility varies; consult the linked source for methodology. Use the comparison tool for side-by-side analysis.

What this model is good for

Based on benchmark scores and capability fit, Qwen3-Coder-480B ranks well for:

• Best Open-Weight Model — rank #2. Best open-weight model for code-heavy workloads.
• Code Generation — rank #4. Best open-weight coder. Significantly cheaper than Claude/GPT-5.

Cost calculator

For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0080 per call. For typical usage:

For more precise estimates including caching discounts, use the LLM API Cost Calculator.

Other Alibaba models

• Qwen3-235B

Common comparisons

• Qwen3-Coder-480B vs GPT-4.1 Side-by-side specs, pricing, and benchmarks
• Qwen3-Coder-480B vs o3 Side-by-side specs, pricing, and benchmarks
• Qwen3-Coder-480B vs Mistral Large 2 Side-by-side specs, pricing, and benchmarks
• Qwen3-Coder-480B vs GPT-4o Side-by-side specs, pricing, and benchmarks

API setup

curl https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3-coder-480b", "messages": [{"role": "user", "content": "Hello"}]}'

See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.