CrossModel
Qwen3.8 Max
qwen/qwen3.8-max
Back to model catalog

Qwen · Model guide

Qwen3.8 Max

Compare
qwen/qwen3.8-max

Qwen's released flagship is a 2.4T-parameter MoE with 95B active, combining a 1M-token context window and native multimodal understanding with adjustable reasoning, coding, office work and long-horizon agents.

Modalities
TextImageVideoText
Context
1M
Max output
131K
Price / 1M tokens
$ 1.88in$ 5.63out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorThe most powerful Qwen model, comprehensively upgraded for coding, office work, research and long-horizon tasks.source

Best for

  • Maximum reasoning · Offers low, medium and xhigh reasoning levels with a large thinking budget.source

  • Multimodal coding agents · Qwen positions the released flagship for top-end coding and agent tools with vision understanding.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 1.88
Output$ 5.63
Cache read$ 0.23
Cache write$ 2.35
Estimate a request
$ 0.0301
Estimated cost per request
10.0K × $ 1.88
+ 2.0K × $ 5.63
≈ $ 30.06 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
131.1K tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Reasoning effort
low · medium · xhigh
Thinking budget
0 – 0 tokens
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsqwen.ai 1qianwenai.com 2Capabilitiesqwen.ai 1qianwenai.com 2help.aliyun.com 3

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.1
    pass_rate·Qwen Team · 2026-08-03Claude Code10 runssetup not fully disclosed

    Five-hour timeout.

    86.6%
Coding
  • SWE-Bench Pro
    resolved_rate·Qwen Team · 2026-08-03Claude Codesetup not fully disclosed

    Corrected task set, 256K context.

    67.7%
Computer use
  • OSWorld Verified
    success_rate·Qwen Team · 2026-08-03setup not fully disclosed
    86.1%
Long context
  • MRCR v2 256K (8-needle)
    score·Qwen Team · 2026-08-03setup not fully disclosed
    92.9%
Multimodal reasoning
  • MMMU Pro
    accuracy·Qwen Team · 2026-08-03setup not fully disclosed
    82.3%
Reasoning
  • Humanity's Last Exam
    accuracy·Qwen Team · 2026-08-03setup not fully disclosed
    43.6%
Research
  • PaperBench (BasicAgent)
    score·Qwen Team · 2026-08-033 runssetup not fully disclosed

    Code-Dev mode, judged by Claude Opus 4.6; up to 12 hours per run.

    93%
Scientific reasoning
  • GPQA Diamond
    accuracy·Qwen Team · 2026-08-03setup not fully disclosed
    92.6%
Tool use
  • Toolathlon Verified
    pass_rate·Qwen Team · 2026-08-03setup not fully disclosed

    Pass@1.

    72.5%
Video understanding
  • VideoMMMU
    accuracy·Qwen Team · 2026-08-03setup not fully disclosed
    88.7%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Qwen3.8 Max?
Qwen3.8 Max is available on CrossModel as qwen/qwen3.8-max. It has a 1M-token context window and can return up to 131K tokens per request.
How much does Qwen3.8 Max cost?
Currently $ 1.88 per 1M input tokens and $ 5.63 per 1M output tokens. Cached input is billed at $ 0.23 per 1M.
Does Qwen3.8 Max support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.