How much does Qwen3 Max Thinking cost?

Qwen3 Max Thinking costs $0.78 per million input tokens and $3.90 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $35.

What is the context length of Qwen3 Max Thinking?

Qwen3 Max Thinking accepts up to 262,144 tokens (262K) of input and can return up to 65,536 tokens in one response.

Does Qwen3 Max Thinking support tool calling and structured outputs?

Yes, Qwen3 Max Thinking supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Log probabilities, Deterministic seed.

What inputs and outputs does Qwen3 Max Thinking support?

Qwen3 Max Thinking accepts Text as input and produces Text as output.

When was Qwen3 Max Thinking released?

Qwen3 Max Thinking was released by Qwen in 2026-02-09.

Qwen3 Max Thinking

qwen3-max-thinking

API Provider site

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it... Built by Qwen.

Prices updated recently

Input price

$0.78

per 1M tokens · Standard

Output price

$3.90

per 1M tokens · Standard

Input limit

262K

tokens

Output limit

66K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

Qwen3 Max Thinking price history

2 price records since 9/25/2026

Qwen3 Max Thinking cost calculator

Input20M tokens

Output5M tokens

$35/month

Standard pricing

Overview

What is Qwen3 Max Thinking?

Qwen3 Max Thinking is a text & reasoning model from Qwen. Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it... Its 262K context window and $0.78 input price make it a candidate for quality-focused production applications.

Content workflowsClassification

Benchmarks

Qwen3 Max Thinking benchmarks & speed

How Qwen3 Max Thinking scores on standardized evaluations, and where it lands among every model we track.

21.3

Intelligence Index

Better than 53% of 153 models

Reasoning

GPQA Diamond

86.1%

Graduate-level scientific reasoning · top 37%

HLE

28.0%

Humanity's Last Exam · top 40%

Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.

Rates

Qwen3 Max Thinking pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$0.78

Per 1M tokens

Cached input · Standard

Not available

No listed cached-input rate

Capabilities

Qwen3 Max Thinking Tools

Tools available when using Qwen3 Max Thinking through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Supported

Built-in web search

Not supported

Log probabilities

Supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Not supported

Strengths and limitations

Strengths

Measured results (AA Intelligence 21.3) position it for demanding production work.
262K context supports large documents, repositories and extended conversations.
Supports text & reasoning workloads in one model.

Limitations

Generated tokens cost 5× more than input tokens, which matters for verbose responses.
Large context capacity does not guarantee consistent retrieval across the entire prompt.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider