Models/Qwen/Qwen3 Max Thinking

Qwen3 Max Thinking

Name: Qwen3 Max Thinking API access
Brand: Qwen

Qwen · Proprietary · Released Feb 9, 2026 · qwen/qwen3-max-thinking

Compare Estimate cost

262K contextToolsReasoningStructured output

Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Alibaba	$0.78	$3.90	—	262K	—	2.4s	38 tok/s	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago

About

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...

Specifications

Context window262,144

Max output65,536

Modalities intext

Modalities outtext

LicenseProprietary

ReleasedFeb 9, 2026

TokenizerQwen

Qwen3.8 27B$0.35 / $2.55 Qwen3.8 2.4T A95B$2.00 / $6.00 Qwen3.8 Max$2.00 / $6.00 Qwen3.7 Flash$0.03 / $0.13

Embed badge

Qwen3 Max Thinking price and speed badge

[![Qwen3 Max Thinking](https://modelindex.ai/badge/qwen/qwen3-max-thinking)](https://modelindex.ai/models/qwen/qwen3-max-thinking)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

ModelIndex benchmarks43 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.