Qwen3.8 2.4T A95B
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.8-2.4t-a95b', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen3.8 2.4T A95B by Alibaba Cloud. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
| 256K | 131K | 1.3s | 58tps | $1.65/M | $4.95/M | Read:$0.12/M Write:— | — | 08/03/2026 | |||||
| 262K | 131K | 1.7s | 209tps | $2/M | $6/M | Read:$0.25/M Write:— | — | 08/03/2026 | |||||
| 262K | 131K | 1.6s | 70tps | $2/M | $6/M | Read:$0.25/M Write:$2.5/M | — | 08/03/2026 | |||||
| 262K | 131K | 1.6s | 66tps | $2/M | $6/M | Read:$0.25/M Write:— | — | 08/03/2026 | |||||
| 262K | 131K | 1.1s | $2/M | $6/M | Read:$0.25/M Write:— | — | 08/03/2026 | ||||||
| 262K | 131K | 1.4s | 128tps | $2/M | $6/M | Read:$0.2/M Write:— | — | 08/03/2026 |
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingMore models by Alibaba Cloud
| Model |
|---|
| 1M | 0.3s | 76tps | $0.10/M | $0.40/M | Read:$0.01/M Write:— | — | +1 |   | 08/14/2026 | ||||
| 1M | 0.7s | 145tps | $2/M | $6/M | Read:$0.25/M Write:$2.5/M | — | +1 |  | 08/02/2026 | ||||
| 991K | 2.1s | 188tps | $0.03/M+2 more | $0.13/M+2 more | Read: $0.01/M+2 more Write: $0.04/M+2 more | — | +2 | | 07/28/2026 | ||||
| 1M | 0.7s | 373tps | $0.40/M+1 more | $1.60/M+1 more | Read: $0.08/M+1 more Write: $0.5/M+1 more | — | +2 | | 06/02/2026 | ||||
| 991K | 0.8s | 156tps | $2.50/M | $7.50/M | Read:$0.5/M Write:$3.13/M | — | | 05/21/2026 | |||||
| 262K | 0.4s | 63tps | $0.20/M | $0.88/M | Read:$0.11/M Write:— | — | | 09/23/2025 |
Copy link to headingAbout Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B was released August 3, 2026 as the open-weight version of Alibaba Cloud's Qwen 3.8 flagship, following the hosted Qwen3.8 Max endpoint that opened earlier the same month.
The architecture is a mixture-of-experts design with 2.4 trillion total parameters and 95 billion active per forward pass, spread across 512 routed experts and 92 layers. What distinguishes it is the attention stack: 69 of those 92 layers use linear attention, with full attention layers interleaved at intervals. In the linear layers a growing KV cache is replaced by a bounded recurrent state, which is what makes long context practical to serve rather than merely supported on paper.
The context window is 262.1K tokens, with up to 131.1K tokens per response. On benchmarks, Qwen3.8 2.4T A95B reaches 86.6 on Terminal Bench 2.1 and leads at 93.0 on PaperBench, while DeepSWE 1.1 at 56.6 and FrontierSWE at 73.5 sit lower relative to the field.
Running the full weights takes serious hardware, at roughly 4.89 TB. Quantized checkpoints bring that down substantially, with 4-bit builds available for both NVIDIA and AMD nodes. Through AI Gateway you skip that entirely and call the model over an API.
You can integrate Qwen3.8 2.4T A95B through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Qwen3.8 2.4T A95B is the open-weight release, and it is not identical to the hosted Qwen3.8 Max endpoint. The open version omits features the cloud model carries, including image input and a non-thinking mode, so a workload that depends on either belongs on Qwen3.8 Max instead.
- Configuration: Open weights here do not mean unrestricted. The license requires model providers earning more than 50 million US dollars in a twelve-month period to obtain a commercial license from Alibaba Cloud. Read the license terms before you build a hosted product on it.
- Configuration: Benchmark results are uneven by task. Qwen3.8 2.4T A95B leads on PaperBench and posts a strong Terminal Bench 2.1 result, but DeepSWE 1.1 and FrontierSWE land lower. If software engineering is the whole workload, compare it against the alternatives below on your own repository.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Qwen3.8 2.4T A95B
Best for
- Open-Weight Frontier Scale: Flagship capability with published weights
- Long-Context Work: A mostly-linear attention stack that stays affordable to serve
- Research And Document Tasks: Its leading PaperBench territory
- Terminal And Agent Workloads: Where its Terminal Bench result is strongest
- Self-Host Optionality: Quantized checkpoints for moving off a hosted API later
Consider alternatives when
- Image Input Needs: The open release omits vision that Qwen3.8 Max carries
- Non-Thinking Mode: Also omitted from the open release
- Pure Software Engineering: DeepSWE 1.1 and FrontierSWE results sit lower
- Unrestricted Licensing: Providers above a revenue threshold need a commercial license
Copy link to headingConclusion
Qwen3.8 2.4T A95B puts Alibaba Cloud's Qwen 3.8 flagship into open weights, with 95B active parameters, 512 experts, and a 262.1K tokens window that linear attention keeps servable. Point alibaba/qwen3.8-2.4t-a95b at AI Gateway to use it without provisioning multi-terabyte hardware, and check the license if you plan to resell access.