Qwen3 Coder 30B A3B Instruct

Qwen · qwen/qwen3-coder-30b-a3b-instruct

← Back to leaderboard

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Qwen3 Coder 30B A3B Instruct ranks #91 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.18 blended per million tokens, it is cheaper than 85% 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: 235929

Pricing

Input / 1M: 0.07
Output / 1M: 0.28
Blend / 1M: 0.18

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.18per 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$0.18
10,000,000$1.75
100,000,000$17.50

Related models

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

More from Qwen

Closest API price