Skip to main content

    Alibaba

    Qwen3-Max-Thinking

    Alibaba's January 2026 Qwen3-Max-Thinking is a text reasoning model with adaptive tool use and a 256K-token context. Its documented Model Studio identity is qwen3-max-2026-01-23. That dated endpoint and the qwen3-max alias are scheduled for retirement on October 10, 2026 at 00:00 UTC+8, subject to the actual rollout time.

    256K tokens
    Text only
    Max
    Provider
    Alibaba
    Context
    256K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Max
    Released
    Jan 26, 2026
    Speed
    Slow
    Reasoning
    Expert
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    21.3points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    86.1%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    64tokens/s
    Artificial Analysis · As of Aug 11, 2026Stale · 31d old

    API pricing

    API input cost
    $0.00/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $0.00/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Qwen3 Max Thinking

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Reasoning
    • Multilingual
    • Chain-of-Thought
    • Asian Languages

    Use cases

    • Multilingual AI
    • East Asian markets
    • Complex reasoning
    • Global enterprises

    Strengths

    • Text reasoning
    • Adaptive tool use
    • 256K context
    • Scheduled Model Studio retirement

    Best for

    Existing integrations preparing to migrate from Qwen3-Max-Thinking

    Use Qwen3-Max-Thinking in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Qwen3-Max-Thinking?
    Alibaba's January 2026 Qwen3-Max-Thinking is a text reasoning model with adaptive tool use and a 256K-token context. Its documented Model Studio identity is qwen3-max-2026-01-23. That dated endpoint and the qwen3-max alias are scheduled for retirement on October 10, 2026 at 00:00 UTC+8, subject to the actual rollout time.
    How much does Qwen3-Max-Thinking cost in yno.ai?
    Qwen3-Max-Thinking is available on the Max tier of yno.ai.
    What can Qwen3-Max-Thinking do?
    Qwen3-Max-Thinking is best for Existing integrations preparing to migrate from Qwen3-Max-Thinking. Its main capabilities include Reasoning, Multilingual, Chain-of-Thought, Asian Languages.
    How does Qwen3-Max-Thinking compare to other models?
    Qwen3-Max-Thinking excels at Text reasoning and is recommended for Multilingual AI, East Asian markets, Complex reasoning, Global enterprises. See related models below.
    How do I use Qwen3-Max-Thinking in yno.ai?
    Sign up for yno.ai, select Qwen3-Max-Thinking from the model picker, and start chatting.