Qwen: Qwen3.8 2.4T A95B
Qwen 3.8 is a language model developed by qwen that handles text input and supports tool integration and reasoning capabilities. It has a context length of up to 1 megabyte and can generate up to 131,072 tokens per completion. This model may be worth considering for users who require robust reasoning and tool support within their applications. At $2/M input and $6/M output tokens, its pricing is comparable to other models in the market. Its blended benchmark score of 73.1 across one independent test indicates a solid performance profile, making it a viable option for projects with moderate computational demands.
Benchmark results
Independent, published benchmarks. Blended score 67.0 across 1 benchmark, last refreshed 2026-09-27. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 65.8 |
- Model ID
- qwen/qwen3.8-2.4t-a95b
- Vendor
- qwen
- Released
- August 2026
- Tokenizer
- Qwen
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 131,072 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $2.00/M input and $6.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.07 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.30 |
| A month of a busy support chatbot | 5M in / 2M out | $22.00 |
Price & spec history
Tracked daily by PicksByModel since 2026-08-13.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-15 | $2.00 | $6.00 | 1,048,576 |
| 2026-08-14 | $2.00 | $6.00 | 1,010,000 |
| 2026-08-13 | $2.00 | $6.00 | 1,000,000 |
Similar models
Qwen: Qwen3.6 Max Preview
Qwen: Qwen3 VL 8B Thinking
Qwen: Qwen3.7 Max
Qwen: Qwen3 Coder 30B A3B Instruct
Qwen: Qwen3 30B A3B Instruct 2507
Qwen: Qwen3 235B A22B Instruct 2507
Quick answers
- How much does Qwen: Qwen3.8 2.4T A95B cost?
- $2.00 per million input tokens and $6.00 per million output tokens.
- What is Qwen: Qwen3.8 2.4T A95B's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does Qwen: Qwen3.8 2.4T A95B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen3.8 2.4T A95B process images?
- No, it is text-only on the input side.