Qwen3 Coder 480B A35B Instruct: API pricing, providers and specs
Qwen3 Coder 480B A35B Instruct is a text model by Alibaba. 15 providers serve it, from $0.95 to $5.16 /1M; the lowest price is at Helicone.
How Qwen3 Coder 480B A35B Instruct compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $0.95 /1M against a median of $1.10; 48% of comparable models cost less.
- Its 262K-token context window is larger than 45% of them (median 262K), about 390 pages of text.
- On LMArena's Text board it ranks #59 of the 120 comparable models scored there.
- 15 providers serve it; 84% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Qwen3 Coder 480B A35B Instruct prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Helicone | $0.22/1M | From$0.95/1M | — | — |
 CometAPI | $0.24/1M | $0.96/1M | — | — |
 Deep Infra | $0.30/1M | From$1/1M | $0.10/1M | — |
 SiliconFlow | $0.25/1M | $1/1M | — | — |
| OpenRouter | $0.30/1M | From$1/1M | $0.10/1M | 262K |
 Venice AI | $0.35/1M | $1.50/1M | $0.04/1M | — |
 Jiekou.AI | $0.38/1M | $1.55/1M | — | — |
| DevPass (LLM Gateway) | $0.38/1M | From$1.55/1M | — | — |
 Requesty | $0.40/1M | From$1.60/1M | $0.40/1M | 262K |
| Vercel AI Gateway | $0.22/1M | $1.80/1M | $0.022/1M | 262K |
 Amazon Bedrock | $0.45/1M | From$1.80/1M | — | — |
 Vertex | $0.22/1M | From$1.80/1M | $0.022/1M | — |
 AIHubMix | $0.82/1M | From$3.28/1M | — | 262K |
 Prime Inference | $0.975/1M | $4.88/1M | — | — |
| AI/ML API | $1.06/1M | $5.16/1M | $1.06/1M | — |
- HeliconeFrom$0.95
- CometAPI$0.96
- SiliconFlow$1
- Deep InfraFrom$1
- OpenRouterFrom$1
- Venice AI$1.50
- Jiekou.AI$1.55
- DevPass (LLM Gateway)From$1.55
- RequestyFrom$1.60
- Vercel AI Gateway$1.80
- Amazon BedrockFrom$1.80
- VertexFrom$1.80
Specs
- Type
- Text
- Maker
- Alibaba
- Inputs
- Text
- Outputs
- Text
- Context
- 262K≈ 390 pages of text
- Max output
- 66K
- Capabilities
- Prompt caching, JSON, Tool calling
- Released
- Jul 22, 2025
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 480B
- Arena score
- 1357Text
- Monthly searches
- 3K
Alternatives to Qwen3 Coder 480B A35B Instruct
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Qwen3 Coder 480B A35B Instructthis model | $0.95/1M | 262K | 1357 | 15 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| GLM-5.2 | $1.80/1M | 1M | 1604 | 44 |
| Grok Build 0.1 | $1.60/1M | 256K | — | 18 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
More from Alibaba
Qwen-Image-2.1Alibaba$0.02/imgQwen3.8 2.4T A95BAlibaba$4.11/1MWan3.0Alibaba$0.025/secQwen3.8 27BAlibaba$0.50/1MWan 2.2Alibaba$0.01/runQwen3.8 Flash NextAlibaba$0.376/1MQwen2-1.5B-InstructAlibaba$0.20/1MQwen3.5 FlashAlibaba$0.287/1MQwen3 Coder 480B A35B Instruct FAQ
The lowest price for Qwen3 Coder 480B A35B Instruct is $0.95 /1M, at Helicone.
Helicone, at $0.95 /1M. 15 providers serve Qwen3 Coder 480B A35B Instruct; the table above lists every one with its price.
Qwen3 Coder 480B A35B Instruct reads up to 262K tokens per request and writes up to 66K.
Yes. Qwen3 Coder 480B A35B Instruct's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 480B, as the safetensors metadata of its official Hugging Face repo states.
15 API providers serve Qwen3 Coder 480B A35B Instruct. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us