Qwen3 Coder 480B A35B pricing & benchmarks
Released Jul 23, 2025 · served by 6 providers
What Qwen3 Coder 480B A35B is
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...
- Model ID:
qwen/qwen3-coder - Modality: text->text
- Knowledge cutoff: 2025-06-30
- Tool calling: supported · Structured output: supported
- Weights:
Qwen/Qwen3-Coder-480B-A35B-Instructon Hugging Face
Providers and prices for Qwen3 Coder 480B A35B
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| DeepInfracheapest | $0.300 | $1.00 | 262K | fp4 | 99.5% | — |
| Venice | $0.350 | $1.50 | 256K | fp8 | 92.9% | — |
| CoreWeave | $1.00 | $1.50 | 262K | bf16 | 95.7% | — |
| Novita | $0.380 | $1.55 | 262K | fp8 | 99.3% | — |
| $0.220 | $1.80 | 262K | — | 100.0% | — | |
| Alibaba | $0.975 | $4.88 | 262K | — | 100.0% | — |
Qwen3 Coder 480B A35B benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| codecategories | models | #62 | 1174 | 61.2% |
| website | models | #63 | 1183 | 61.7% |
| gamedev | models | #64 | 1157 | 59% |
| uicomponent | models | #64 | 1151 | 61.5% |
| dataviz | models | #83 | 1111 | 54.9% |
FAQ
How much does the Qwen3 Coder 480B A35B API cost?
$0.220 per 1M input tokens and $1.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.52.
Is Qwen3 Coder 480B A35B free?
No. It is a paid model starting at $0.220 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Qwen3 Coder 480B A35B?
DeepInfra at $0.300 input / $1.00 output per 1M tokens (fp4 quantization).
Can I self-host Qwen3 Coder 480B A35B?
Yes — weights are published as Qwen/Qwen3-Coder-480B-A35B-Instruct on Hugging Face, so you can run it on your own hardware.