Qwen: Qwen3 Coder 480B A35B (exacto)
Analysis Summary
Qwen: Qwen3 Coder 480B A35B (exacto) sits in the Legacy tier on our leaderboard, ranked #363 of 556 published models on overall intelligence. At $0.220 input and $1.80 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and reasoning.
Editorial notes
Qwen3 Coder 480B A35B (exacto) mirrors the standard variant with no benchmark data available; tool use support and low pricing are positives but unverified performance caps confidence; -4 penalty applied for provider accessibility.
Assessed May 14, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
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 repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.
Capabilities
How does Qwen: Qwen3 Coder 480B A35B (exacto) stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
qwen/qwen3-coder:exacto
|
| Provider | qwen |
| Release Date | July 23, 2025 |
| Context Length | 262,144 tokens |
| Max Completion | 65,536 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.22 | $0.000220 |
| Output | $1.80 | $0.001800 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
