Qwen: Qwen3 Coder 480B A35B (exacto)
Qwen3 Coder 480B A35B (exacto) is a variant of the same large coding model with slightly higher output pricing and no benchmark data, making it difficult to differentiate from the standard version on merit. Without performance evidence, it scores conservatively alongside its sibling.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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
Architecture
| Modality | Text → Text |
| Tokenizer | Qwen3 |
Model Information
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 — refreshed every 30 minutes.
