Qwen3 Coder 480B A35B

Qwen · qwen/qwen3-coder

← Back to leaderboard

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...

Qwen3 Coder 480B A35B ranks #162 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.65 blended per million tokens, it is cheaper than 62% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 262144
Max output: 65536

Pricing

Input / 1M: 0.30
Output / 1M: 1.00
Blend / 1M: 0.65

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.65per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.65
10,000,000$6.50
100,000,000$65.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Qwen

Closest API price