Qwen3.8-2.4T-A95B
The open-weight release of Qwen3.8-Max: a 2.4-trillion-parameter sparse MoE with 95B active parameters, positioned around autonomous coding, workplace tasks, and long-horizon execution.
Qwen3.8-2.4T-A95B is available on MiniRouter as . The model page has current pricing, provider routes and API setup.
About the model
- Architecture: 2.4T MoE · 95B active. 512 experts with hybrid Gated DeltaNet and gated attention
- Context: 262K native. Extensible toward 1M; the hosted API documents a 1M window
- Weights: Released. Qwen3.8-Max License: source-available with revenue-gated terms
- Reasoning: Always on. The open checkpoint requires thinking mode for all interactions
Publisher pricing
Pricing below comes from the linked publisher sources and does not represent a MiniRouter route or price.
| Phase | Input / 1M | Output / 1M | Blended / 1M | Effective | Source |
|---|---|---|---|---|---|
| Model Studio API | $1.65 | $4.951 | $2.47525 | Aug 3, 2026 – open-ended | Alibaba Cloud ↗ |
Publisher-reported benchmarks
Results from the publisher’s announcement, grouped by unit.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| Terminal Bench 2.1 | 86.6 | Alibaba Cloud | Aug 3, 2026 | Announcement ↗ |
| SWE-bench Pro | 67.7 | Alibaba Cloud | Aug 3, 2026 | Announcement ↗ |
| DeepSWE 1.1 | 56.6 | Alibaba Cloud | Aug 3, 2026 | Announcement ↗ |
| GPQA Diamond | 92.6 | Alibaba Cloud | Aug 3, 2026 | Announcement ↗ |
| HLE | 43.6 | Alibaba Cloud | Aug 3, 2026 | Announcement ↗ |
Alibaba's hosted qwen3.8-max API is documented as multimodal, while the open-weight A95B checkpoint is text-only with mandatory thinking.
Listed pricing is the Model Studio rate for most regions; Singapore bills $2 / $6 per 1M tokens.
Alibaba reports the benchmark figures; MiniRouter has not reproduced them.
Independent measurements
Artificial Analysis evaluations of the first-party API.
Qwen3.8 2.4T A95B ranks #18 of 462 model families on their Intelligence Index.
- Intelligence Index
- 39.9
- Composite of their evaluations
- Coding Index
- 71.9
- Coding evaluations only
- Blended price
- $3
- USD per 1M tokens, 3:1 input to output, first-party list
- Output speed
- 41
- Median tokens per second
- First answer token
- 51s
- Median seconds, including reasoning
Qwen3.8 2.4T A95B on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 21, 2026. Measured on the model's first-party API, not a MiniRouter route.
Keep exploring
Compare published results in the model rankings and coding benchmarks, or read more model releases.
For MiniRouter product updates, visit the changelog.
Sources
- Read at Alibaba Cloud ↗
Alibaba Cloud announcement
Published Aug 3, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 21, 2026
Editorial reference revised 2026-09-29. Catalog status comes from the generated routing snapshot.