# Qwen3 30B A3B API pricing

No price from the maker itself is on record for Qwen3 30B A3B. The lowest of 14 providers is Helicone: $0.08 per 1M input tokens and $0.29 per 1M output tokens (as of 2026-11-12). Context window: 41K tokens, up to 16.4K output tokens per request.

- Type: Text
- Context: 41K
- Max output: 16.4K
- Released: 2025-04-28
- Open weights: Yes

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

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Helicone](https://helicone.ai/models) | qwen3-30b-a3b | $0.08 | $0.29 | — | Lowest |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | qwen3-30b-a3b | $0.095 | $0.285 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | greenference/qwen3-30b-a3b | $0.095 | $0.285 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | qwen/qwen3-30b-a3b | $0.1 | $0.3 | $0.05 |  |
| [Jiekou.AI](https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev) | qwen/qwen3-30b-a3b-fp8 | $0.09 | $0.45 | — |  |
| [Deep Infra](https://deepinfra.com/models) | Qwen/Qwen3-30B-A3B | $0.12 | $0.5 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | Qwen/Qwen3-30B-A3B | $0.12 | $0.5 | — |  |
| [Kilo Gateway](https://kilo.ai) | qwen/qwen3-30b-a3b | $0.12 | $0.5 | — |  |
| [OpenRouter](https://openrouter.ai/models) | qwen/qwen3-30b-a3b | $0.12 | $0.5 | — |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | alibaba/qwen-3-30b | $0.12 | $0.5 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | qwen/qwen3-30b-a3b | $0.108 | $1.076 | $0.0216 |  |
| [302.AI](https://doc.302.ai) | qwen3-30b-a3b | $0.11 | $1.08 | — |  |
| [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/) | @cf/qwen/qwen3-30b-a3b-fp8 | $0.0509 | $0.335 | — | Deprecated |
| [Qiniu](https://developer.qiniu.com/aitokenapi) | qwen3-30b-a3b | $0.108696 | $0.434783 | — | Deprecated |

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/qwen3-30b-a3b/