Qwen3-Coder 480B-A35B InstructDeprecatedOpen weights
Alibaba · released 2025-04
The official API price of Qwen3-Coder 480B-A35B Instruct is $1.5 per 1M input tokens and $7.5 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 21 providers sell it. The lowest is NanoGPT: $0.13 input, $0.5 output. This model is marked as deprecated.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialTiered pricingDeprecatedqwen3-coder-480b-a35b-instruct | $1.5 | $7.5 | — | OfficialTiered pricingDeprecated | Official docs |
NNanoGPTLowestqwen/ | $0.13 | $0.5 | $0.065 | Lowest | Official docs |
 submodelQwen/ | $0.2 | $0.8 | — | Official docs | |
HHeliconeqwen3-coder | $0.22 | $0.95 | — | Official docs | |
 SiliconFlowQwen/ | $0.25 | $1 | — | Official docs | |
 Deep InfraQwen/ | $0.3 | $1 | $0.1 | Official docs | |
KKilo Gatewayqwen/ | $0.3 | $1 | $0.1 | Official docs | |
 OpenRouterqwen/ | $0.3 | $1 | $0.1 | Official docs | |
AAbacusQwen/ | $0.38 | $1.55 | — | Official docs | |
JJiekou.AIqwen/ | $0.38 | $1.55 | — | Official docs | |
EEden AIdeepinfra/ | $0.4 | $1.6 | — | Official docs | |
MMerge Gatewayqwen/ | $0.22 | $1.8 | — | Official docs |
9 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Vercel AI GatewayTiered pricingalibaba/ | $0.22 | $1.8 | $0.022 | Tiered pricing | Official docs |
 IO.NETIntel/ | $0.46125 | $2.29375 | $0.230625 | Official docs | |
 Hugging FaceQwen/ | $2 | $2 | — | Official docs | |
3302.AITiered pricingqwen3-coder-480b-a35b-instruct | $0.86 | $3.43 | — | Tiered pricing | Official docs |
 AI/ML APIalibaba/ | $1.058 | $5.15775 | $1.058 | Official docs | |
 Amazon BedrockDeprecatedqwen. | $0.45 | $1.8 | — | Deprecated | Official docs |
 OpenCodeDeprecatedqwen3-coder | $0.45 | $1.8 | — | Deprecated | Official docs |
 Together AIDeprecatedQwen/ | $2 | $2 | — | Deprecated | Official docs |
QQiniuTiered pricingDeprecatedqwen3-coder-480b-a35b-instruct | $0.869565 | $3.478261 | — | Tiered pricingDeprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Open Qwen coding heavyweight for repository reasoning and agentic engineering
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 65.5K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-04
- Open weights
- Yes
- Released
- 2025-04
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.