/ Models

Language models

Qwen: Qwen3 Coder 480B A35B

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...

Maker
Qwen
Context window
262K
Max output
66K
Input / 1M
$0.3
Output / 1M
$1
1M in + 1M out
$1.30

Everything else

Max output66K
Input / 1M$0.3
Output / 1M$1
Cache read / 1M$0.1
Cache write / 1M
1M in + 1M out$1.30
Takestext
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2025-07-23
Knowledge cutoff2025-06-30
Retires
Catalog idqwen/qwen3-coder

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models