# Qwen3 8B API pricing

The official API price of Qwen3 8B is $0.18 per 1M input tokens and $0.7 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 8.2K output tokens per request. 6 providers sell it. The lowest is SiliconFlow: $0.06 input, $0.06 output. This model is marked as deprecated.

- Type: Text
- Context: 131K
- Max output: 8.2K
- Released: 2025-04
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Alibaba](https://www.alibabacloud.com/help/en/model-studio/models) | qwen3-8b | $0.18 | $0.7 | — | Official, Deprecated |
| [SiliconFlow](https://cloud.siliconflow.com/models) | Qwen/Qwen3-8B | $0.06 | $0.06 | — | Lowest |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | Qwen/Qwen3-8B | $0.07 | $0.18 | — |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | Qwen/Qwen3-8B | $0.195 | $0.6 | $0.039 |  |
| [NanoGPT](https://docs.nano-gpt.com) | qwen/qwen3-8b | $0.47 | $0.47 | — |  |
| [SiliconFlow (China)](https://cloud.siliconflow.com/models) | Qwen/Qwen3-8B | $0 | $0 | — |  |

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.

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.

https://apibook.ai/models/alibaba/qwen3-8b/