Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is a large language model made by Qwen, added to the catalog on 12 Aug 2026. It has a context window of 1,048,576 tokens and costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. It accepts text and produces text. Typical uses: summarising long documents, long-context question answering and generating structured data.
Price checked ยท source: OpenRouter
What Qwen3.8 2.4T A95B is
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen. It accepts text and produces text. The catalog lists 95 billion active parameters out of 2.4 trillion total. Its context window is 1,048,576 tokens, and its maximum output is 131,072 tokens. That context capacity can suit requests that include extensive text, such as a long document or several related passages, while the output limit permits lengthy generated responses. Both figures describe token limits, not a guarantee that every request will use the full allowance.
The model supports reasoning, tools, structured outputs, and response formats. These features make it suitable for text workflows that ask for analysis, use tools through a supported integration, or require responses in a specified format. Its listed input and output modalities are text, so the catalog supports describing language-based uses rather than image or audio tasks. Possible tasks include summarizing documents, answering questions about supplied material, drafting text, generating structured responses, and coding assistance. Tool use may be relevant when a workflow connects the model to tools; the catalog does not identify particular tools or formats. The model is described as an open-weight variant of Qwen3.8 Max. The catalog does not provide further detail about its supported languages or specialized performance, so its listed context, modalities, and capabilities are the basis for assessing fit.
Key features
- Accepts text and produces text
- Supports a context window of 1,048,576 tokens
- Maximum output length of 131,072 tokens
- Supports reasoning and tool use
- Supports structured outputs and response formats
Typical uses
- Summarising long documents
- Long-context question answering
- Generating structured data
- Coding assistance
- Tool-supported research
Qwen3.8 2.4T A95B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $2.00 |
| Output, per 1M tokens | $6.00 |
| Cached input read, per 1M tokens | $0.25 |
No price change since it was added on 12 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0028 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.055 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.072 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.309 |
Qwen3.8 2.4T A95B specifications
| Model id | qwen/qwen3.8-2.4t-a95b |
|---|---|
| Version | qwen3.8-2.4t-a95b-20260812 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 12 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Qwen3.8 2.4T A95B yet.
Compare Qwen3.8 2.4T A95B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.