Qwen 3.8 API

alibaba/qwen3.8-max
Qwen3.7-Max is Alibaba's most capable large language model, engineered from the ground up for advanced reasoning, autonomous agent workflows, and serious coding productivity.
Context
1M tokens
Input
$2.6 / 1M tokens
Output
$7.8 / 1M
Released
Jul 24, 2026

How to use Qwen 3.8 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/qwen3.8-max.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "alibaba/qwen3.8-max",
      "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-max",
    "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-max","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Qwen 3.8 API Pricing

TypePrice
Input
$2.6 / 1M tokens
Output
$7.8 / 1M
Cached input
$0.325 / 1M tokens

Qwen 3.8 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
40.3
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
71.8
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
OSWorld
84.3
Computer-use across real desktop applicationsSourceSeptember 21, 2026

Qwen 3.8 vs other models

ModelInputOutputContextBest for
Qwen 3.8
This page
$2.6 / 1M tokens
$7.8 / 1M
1M tokens
Multimodal reasoning + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents
$6.877 / 1M tokens
$32.5 / 1M tokens
1M tokens
Chat + assistants
$0.5655 / 1M tokens
$1.131 / 1M tokens
1M tokens
Reasoning + agents
$0.26 / 1M tokens
$1.56 / 1M tokens
1M tokens
Fast, high-volume tasks

Frequently asked questions

Qwen 3.8 has a 1,000,000 tokens context window and can return up to 131,072 tokens.

Qwen 3.8 takes video, image, text as input and returns text.

Use alibaba/qwen3.8-max as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Qwen 3.8 became available on July 24, 2026.

Qwen 3.8 is priced at input $2.6 / 1M tokens, output $7.8 / 1M, cached input $0.325 / 1M tokens.

Yes, Qwen 3.8 can stream responses as they are generated.

Yes, Qwen 3.8 accepts image input alongside text.

Qwen 3.8 was built by Alibaba Cloud.

Start building with Qwen 3.8

Get API Key
1000+ models, one API.