Qwen3.8-Max is Alibaba's flagship reasoning and agentic LLM, positioned as its highest-capability tier for complex multi-step reasoning, coding and autonomous workflows. It is natively multimodal, accepting text and images and returning text, with a 1M-token context window.
It supports hybrid thinking mode, function calling, built-in tools (including web search) and structured outputs.
Released August 3, 2026.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Qwen3.8 Max is documented as suited to autonomous coding and long-horizon execution, including completing full projects over extended periods without human intervention. It is also suited to complex real-world professional work such as legal document review, financial research, application design, and sports analytics.
The model is documented as suited to multimodal content creation, including editing personal footage into vlogs, generating educational animations from text prompts, and building interactive games or applications from natural-language requests. It is also suited to visual tasks such as reconstructing frontend web projects from screenshots and transforming 2D floor plans into 3D interior visualizations.
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.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Function/tool calls are billed separately at $0.013 per call.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 40.3 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 71.8 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| GPQA Diamond | 92.6 | Google-proof graduate science questions (hardest subset) | Source | September 21, 2026 |
| Humanity's Last Exam | 43.6 | Expert-level questions across many domains | Source | September 21, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Qwen3.8 Max This page | Complex reasoning, coding and agentic workflows | |||
| Frontier reasoning + agents | ||||
| Reasoning + agents | ||||
| Complex agentic coding and enterprise workflows | ||||
| Long-context, multimodal & agentic workflows |
Qwen3.8 Max has a 1,000,000 tokens context window and can return up to 131,072 tokens.
Qwen3.8 Max takes 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.
Qwen3.8 Max became available on August 3, 2026.
Qwen3.8 Max is priced at input $2.6 / 1M tokens, output $7.8 / 1M tokens, cached input $0.325 / 1M tokens.
Yes, Qwen3.8 Max can stream responses as they are generated.
Yes, Qwen3.8 Max accepts image input alongside text.
Qwen3.8 Max was built by Alibaba Cloud.
