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.
Routable on MicroRouter
Use alibaba/qwen3.8-2.4t-a95b via the API →- 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 release announcement and does not represent a MicroRouter route or price.
| Phase | Input / 1M | Output / 1M | Blended / 1M | Effective | Source |
|---|---|---|---|---|---|
| Model Studio API | $1.65 | $4.95 | $2.48 | Aug 3, 2026 – open-ended | Alibaba Cloud ↗ |
Publisher-reported benchmarks
Results are grouped by unit. Percentage, Elo, and task-count results never share a scale.
| 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; MicroRouter has not reproduced them.
Independent measurements
Artificial Analysis runs its own evaluations and timing against each model's first-party API. These are the only numbers on this page not reported by the publisher.
Qwen3.8 2.4T A95B ranks #10 of 448 model families on their Intelligence Index.
- Intelligence Index
- 57.7
- 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
- 39
- Median tokens per second
- First answer token
- 53s
- Median seconds, including reasoning
Qwen3.8 2.4T A95B on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 2, 2026. Measured on the model's first-party API, not a MicroRouter route.
What is not independently confirmed
- Every figure on this page is self-reported by the cited publisher. MicroRouter did not run these benchmarks.
- Benchmark harnesses are not standardised. Results sharing a name across vendors have not been confirmed to use identical runs.
- Publisher pricing can change, and introductory phases have stated end dates.
- Qwen3.8-2.4T-A95B is routable through MicroRouter today; live pricing on its model page is authoritative over the publisher figures here.
Related coverage
Other release dossiers and the current MicroRouter catalog.
Sources
- Read at Alibaba Cloud ↗
Alibaba Cloud announcement
Published Aug 3, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 2, 2026
Editorial reference revised 2026-09-02. Catalog status comes from the generated routing snapshot.