Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is the open-weight release of Alibaba Cloud's Qwen 3.8 flagship, a 2.4-trillion-parameter Mixture-of-Experts model with 95B active per token and a context window of 262.1K tokens.
View API reference- Input and output price
- Prices from: Input $1.65, Output $4.95, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
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 | 1.5 s | 52 tps | $1.65/M | $4.95/M | Read$0.12/M | — | 08/03/2026 | ||||||
| 262K | 131K | 0.7 s | 208 tps | $2/M | $6/M | Read$0.25/M | — | 08/03/2026 | ||||||
| 262K | 131K | 2.0 s | 63 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | 08/03/2026 | ||||||
| 262K | 131K | 1.6 s | 56 tps | $2/M | $6/M | Read$0.25/M | — | 08/03/2026 | ||||||
| 262K | 131K | 0.3 s | 109 tps | $2/M | $6/M | Read$0.25/M | — | 08/03/2026 | ||||||
| 262K | 131K | $2/M | $6/M | Read$0.20/M | — | 08/03/2026 | ||||||||
| 256K | 128K | 0.3 s | $2.50/M | $6.25/M | Read$0.50/M | — | 08/03/2026 |
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
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.
Getting started
Call Qwen3.8 2.4T A95B through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.8-2.4t-a95b', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen3.8 2.4T A95B request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.8-2.4t-a95b', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. alibaba/qwen3.8-2.4t-a95b. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen3.8 2.4T A95B supports up to 131,072 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 262K-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK alibaba provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.8-2.4t-a95b', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['deepinfra', 'fireworks'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.8-2.4t-a95b', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.8-2.4t-a95b', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Alibaba Cloud
| Model |
|---|
| 991K | 3.9 s | 50 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 | | 09/01/2026 | |||||
| 991K | 1.1 s | 96 tps | $0.16/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +2 | | 08/26/2026 | |||||
| 1M | 0.6 s | 133 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +3 | 08/14/2026 | |||||
| 1M | 2.5 s | 154 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +1 |  | 08/02/2026 | |||||
| 991K | 2.5 s | 140 tps | $0.03/M+2 more | $0.13/M+2 more | Read$0.006/M Write$0.04/M | — | +2 | | 07/28/2026 | |||||
| 1M | 2.0 s | 58 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +2 | | 06/02/2026 |
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.
Copy link to headingFrequently Asked Questions
How is Qwen3.8 2.4T A95B different from Qwen3.8 Max?
Qwen3.8 2.4T A95B is the open-weight release and Qwen3.8 Max is the hosted endpoint. The open version omits some cloud features, including image input and a non-thinking mode.
How many parameters does Qwen3.8 2.4T A95B use per request?
95 billion active out of 2.4 trillion total, routed across 512 experts. Only the active parameters take part in any single forward pass.
What is the context window for Qwen3.8 2.4T A95B?
The context window is 262.1K tokens, with up to 131.1K tokens per response. Linear attention on most layers replaces a growing KV cache with a bounded recurrent state, which is what keeps long context servable.
Is Qwen3.8 2.4T A95B free to use commercially?
The weights are open but the license is not unrestricted. Model providers earning more than 50 million US dollars in a twelve-month period must obtain a commercial license from Alibaba Cloud. Read the license before building a hosted product on it.
How does Qwen3.8 2.4T A95B perform on coding benchmarks?
Unevenly. It reaches 86.6 on Terminal Bench 2.1, but DeepSWE 1.1 at 56.6 and FrontierSWE at 73.5 sit lower relative to the field. Benchmark it on your own repository before committing a coding workload.
Do I need my own hardware to run Qwen3.8 2.4T A95B?
Not through AI Gateway. Self-hosting the full weights takes roughly 4.89 TB, though 4-bit quantized checkpoints reduce that substantially for NVIDIA and AMD nodes.
Does Qwen3.8 2.4T A95B support Zero Data Retention?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Your use is subject to Alibaba Cloud's Terms & Privacy Policies.