# Qwen3.6 35B-A3B API pricing

The official API price of Qwen3.6 35B-A3B is $0.375 per 1M input tokens and $2.25 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 40 providers sell it. The lowest is engy: $0.045 input, $0.3 output.

- Type: Text
- Context: 262K
- Max output: 65.5K
- Released: 2026-04-17
- 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) | qwen3.6-35b-a3b | $0.375 | $2.25 | — | Official |
| [engy](https://engy.ai/pricing) | qwen3.6-35b-a3b | $0.045 | $0.3 | $0.015 | Lowest |
| [Boundless](https://inference.boundless.network/models) | qwen3.6 | $0.04 | $0.35 | $0.02 |  |
| [EmpirioLabs AI](https://docs.empiriolabs.ai) | qwen3-6-35b-a3b | $0.07 | $0.42 | $0.035 |  |
| [Zenifra](https://docs.zenifra.com) | alibaba/qwen3.6-35b-a3b | $0.19 | $0.48 | — |  |
| [SaladCloud AI Gateway](https://docs.salad.com/ai-gateway/explanation/overview) | qwen3.6-35b-a3b | $0.09 | $0.6 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | qwen/qwen3.6-35b-a3b | $0.112 | $0.8 | $0.056 |  |
| [NanoGPT](https://docs.nano-gpt.com) | qwen/qwen3.6-35b-a3b:thinking | $0.112 | $0.8 | $0.056 |  |
| [Neuralwatt](https://portal.neuralwatt.com/docs) | qwen3.6-35b-flex | $0.1885 | $0.7475 | $0.01885 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | Qwen/Qwen3.6-35B-A3B | $0.1 | $0.89 | $0.035 |  |
| [Kilo Gateway](https://kilo.ai) | qwen/qwen3.6-35b-a3b | $0.1 | $0.9 | $0.025 |  |
| [OpenRouter](https://openrouter.ai/models) | qwen/qwen3.6-35b-a3b | $0.1 | $0.9 | $0.025 |  |
| [Deep Infra](https://deepinfra.com/models) | Qwen/Qwen3.6-35B-A3B | $0.1 | $0.95 | $0.1 |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | Qwen/Qwen3.6-35B-A3B | $0.15 | $0.95 | — |  |
| [Venice AI](https://docs.venice.ai) | qwen3-6-35b-a3b | $0.1 | $1 | — |  |
| [Ambient](https://ambient.xyz) | qwen/qwen3.6-35b-a3b | $0.15 | $1 | $0.15 |  |
| [Umans AI](https://app.umans.ai/offers/code/docs/orgs) | umans-flash | $0.15 | $1 | $0.05 |  |
| [NEAR AI Cloud](https://docs.near.ai/) | Qwen/Qwen3.6-35B-A3B-FP8 | $0.17 | $1.1 | $0.056 |  |
| [Neuralwatt](https://portal.neuralwatt.com/docs) | qwen3.6-35b | $0.29 | $1.15 | $0.029 |  |
| [Neuralwatt](https://portal.neuralwatt.com/docs) | qwen3.6-35b-fast | $0.29 | $1.15 | $0.029 |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/qwen3.6-35b-a3b | $0.2 | $1.27 | $0.056 |  |
| [evroc](https://docs.evroc.com/products/think/overview.html) | Qwen/Qwen3.6-35B-A3B | $0.345 | $1.38 | — |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | qwen3.6-35b-a3b | $0.248 | $1.485 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/qwen3.6-35b-a3b | $0.248 | $1.485 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | qwen/qwen3.6-35b-a3b | $0.248 | $1.485 | $0.0496 |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | qwen/qwen3.6-35b-a3b | $0.248 | $1.485 | — |  |
| [Opper](https://opper.ai/models) | qwen3.6-35b-a3b | $0.248 | $1.485 | — |  |
| [OrcaRouter](https://docs.orcarouter.ai) | qwen/qwen3.6-35b-a3b | $0.248 | $1.485 | — |  |
| [AIHubMix](https://docs.aihubmix.com) | qwen3.6-35b-a3b | $0.254 | $1.524 | — |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | Qwen/Qwen3.6-35B-A3B | $0.45 | $1.335 | $0.09 |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | Qwen/Qwen3.6-35B-A3B:peft:262144 | $0.45 | $1.335 | $0.09 |  |
| [SiliconFlow (China)](https://cloud.siliconflow.com/models) | Qwen/Qwen3.6-35B-A3B | $0.269005 | $1.614033 | — |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | qwen3.6-35b-a3b | $0.279 | $1.671 | — |  |
| [Scaleway](https://www.scaleway.com/en/docs/generative-apis/) | qwen3.6-35b-a3b | $0.280375 | $1.68225 | — | Beta |
| [302.AI](https://doc.302.ai) | qwen3.6-35b-a3b | $0.28 | $1.7 | — |  |
| [SiliconFlow](https://cloud.siliconflow.com/models) | Qwen/Qwen3.6-35B-A3B | $0.24 | $1.8 | $0.15 |  |
| [GreenPT](https://docs.greenpt.ai) | qwen3.6-35b-a3b | $0.342 | $2.052 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | alibaba/qwen3.6-35b-a3b | $0.375 | $2.25 | — |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | alibaba/qwen3.6-35b-a3b | $0.375 | $2.25 | — |  |
| [LLMTR](https://llmtr.com/docs) | qwen3-6-35b | $5 | $10 | — |  |
| [AKI.IO](https://aki.io/docs/) | qwen3.6-35b | $0.168225 | $0.56075 | — | Deprecated |
| [Hetzner](https://experiments.hetzner.com/docs/inference) | Qwen/Qwen3.6-35B-A3B-FP8 | $0 | $0 | $0 | Beta |
| [InferX](https://model.inferx.net/endpoints) | Qwen3.6-35B-A3B-FP8 | $0 | $0 | — |  |
| [InferX](https://model.inferx.net/endpoints) | Qwen3.6-35B-A3B-fp8-no-thinking | $0 | $0 | — |  |
| [NaN](https://nan.builders/docs/models) | qwen3.6 | $0 | $0 | — |  |
| [QVAC](https://www.npmjs.com/package/@qvac/ai-sdk-provider) | qwen3.6-35b-a3b | $0 | $0 | — |  |
| [Umans AI Coding Plan](https://app.umans.ai/offers/code/docs) | umans-flash | $0 | $0 | $0 |  |
| [Umans AI Coding Plan](https://app.umans.ai/offers/code/docs) | umans-qwen3.6-35b-a3b | $0 | $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/qwen3.6-35b-a3b/