# Qwen3.8 2.4T A95B

> Qwen3.8 2.4T A95B is an open-weight language model from Alibaba (Qwen), released on 12 Aug 2026. It accepts text and generates text, with a 262K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $2 per million input tokens and $6 per million output tokens (DeepInfra), across 6 providers we track.

Source page: https://www.aimodel.directory/models/qwen3-8-2-4t-a95b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 12 Aug 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)
- **License:** qwen3.8-max (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)
- **Parameters:** 2.4T (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.8-2.4T-A95B.toml)
- **Hugging Face:** Qwen/Qwen3.8-2.4T-A95B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepInfra | $2 | $6 | $0.20 | 262K |
| SiliconFlow | $2 | $6 | $0.25 | 1M |
| Fireworks AI | $2 | $6 | $0.25 | 262K |
| Vercel AI Gateway | $2 | $6 | $0.25 | 262K |
| OpenRouter | $2 | $6 | $0.25 | 1M |
| Hugging Face Inference Providers | $2.50 | $6.25 | – | 262K |

## FAQ

### What is the context window of Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B has a context window of 262,144 tokens (262K) and can generate up to 131,072 tokens in a single response, according to models.dev.

### How much does the Qwen3.8 2.4T A95B API cost?

Qwen3.8 2.4T A95B is listed from $2 per million input tokens and $6 per million output tokens (DeepInfra). Prices last verified 4 Oct 2026.

### Is Qwen3.8 2.4T A95B open source?

Qwen3.8 2.4T A95B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.8-2.4T-A95B under the qwen3.8-max license. Check the license terms before commercial use.

### When was Qwen3.8 2.4T A95B released?

Alibaba (Qwen) released Qwen3.8 2.4T A95B on 12 Aug 2026, according to models.dev.

### Which providers offer Qwen3.8 2.4T A95B?

We track Qwen3.8 2.4T A95B on 6 providers: DeepInfra, SiliconFlow, Fireworks AI, Vercel AI Gateway, OpenRouter, Hugging Face Inference Providers.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3.8 2.4T A95B", https://www.aimodel.directory/models/qwen3-8-2-4t-a95b