Qwen3-Coder: Benchmarks, Pricing & Size
Qwen3-Coder is a language model from Qwen, released in January 2025.
Qwen3-Coder is an advanced coding model with 480B parameters and 35B active parameters. This is a convenience alias for qwen3-coder-480b-a35b-instruct. It excels at code generation, understanding, and software development tasks with a
Qwen3-Coder pricing
Providers
Qwen3-Coder starts at $0.180 per million input tokens and $0.180 per million output tokens via DeepInfra. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Max Input | Max Output | Latency p95 s | Throughput P95 | Quant | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.180 | $0.180 | 256.0K | 256.0K | — | — | a35b | ||
 Fireworks | $0.250 | $0.250 | 256.0K | 256.0K | — | — | a35b |
Qwen3-Coder model size
Qwen3-Coder has 480 billion parameters. See how it compares to other models in the same parameter range.
Qwen3-Coder API
API access coming soon
Qwen3-Coder will be available through our gateway shortly.
Qwen3-Coder examples
Recent arena outputs from Qwen3-Coder, picked from the highest-ranked matchups.
Qwen3-Coder license
Qwen3-Coder is released under the Apache 2.0 license, which permits commercial use, has 480.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 480.0B
Apache License 2.0 - allows commercial use
FAQ
Common questions about Qwen3-Coder.