import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "alibaba/qwen3.8-2.4t-a95b", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "alibaba/qwen3.8-2.4t-a95b", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"alibaba/qwen3.8-2.4t-a95b","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
This model’s documented pricing caveat is that Alibaba Cloud’s page shows the original API pricing only, excluding limited-time promotions, and it lists separate rates for cache hits and explicit cache creation[2
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 40 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 71.9 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Qwen3.8 2.4T A95B This page | Agentic workflows and structured output |
Qwen3.8 2.4T A95B has a 262,144 tokens context window and can return up to 52,429 tokens.
Qwen3.8 2.4T A95B takes text as input and returns text.
Use alibaba/qwen3.8-2.4t-a95b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Qwen3.8 2.4T A95B became available on August 12, 2026.
Qwen3.8 2.4T A95B is priced at input $3.4385 / 1M tokens, output $8.59625 / 1M tokens, cached input $0.6877 / 1M tokens.
Yes, Qwen3.8 2.4T A95B can stream responses as they are generated.
Qwen3.8 2.4T A95B was built by Alibaba Cloud.
It is a text-only model, accepting text input and producing text output.
It is built for reasoning-focused chat with tool use and structured output support, and reasoning is always enabled.
