Skip to main content

    Alibaba

    Qwen3-Coder

    Alibaba released Qwen3-Coder-480B-A35B-Instruct on July 22, 2025: a 480B-parameter MoE with 35B active parameters for coding agents. It supports 256K tokens natively and extension to 1M with YaRN. Model Studio schedules qwen3-coder-plus and qwen3-coder-480b-a35b-instruct for retirement on October 10, 2026 at 00:00 UTC+8, subject to rollout timing; this is a hosted-endpoint retirement, not withdrawal of published weights.

    256K tokens
    Text only
    Pro
    Provider
    Alibaba
    Context
    256K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Pro
    Released
    Jul 22, 2025
    Speed
    Medium
    Reasoning
    Advanced
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    11.9points
    Artificial Analysis · Date unknownAge unknown
    LiveCodeBench
    58.5%
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    61.8%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    102tokens/s
    Artificial Analysis · As of Aug 11, 2026Stale · 31d old

    API pricing

    API input cost
    $1.50/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $7.50/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Qwen3 Coder 480B A35B Instruct

    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

    • Code
    • Multilingual Code
    • Debugging
    • Refactoring

    Use cases

    • Code generation
    • Review
    • Multilingual codebases
    • East Asian dev teams

    Strengths

    • 480B MoE / 35B active
    • 256K native context
    • Up to 1M with YaRN
    • Published coding-model weights

    Best for

    Teams using the original Qwen3-Coder weights or migrating legacy hosted integrations

    Use Qwen3-Coder in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Qwen3-Coder?
    Alibaba released Qwen3-Coder-480B-A35B-Instruct on July 22, 2025: a 480B-parameter MoE with 35B active parameters for coding agents. It supports 256K tokens natively and extension to 1M with YaRN. Model Studio schedules qwen3-coder-plus and qwen3-coder-480b-a35b-instruct for retirement on October 10, 2026 at 00:00 UTC+8, subject to rollout timing; this is a hosted-endpoint retirement, not withdrawal of published weights.
    How much does Qwen3-Coder cost in yno.ai?
    Qwen3-Coder is available on the Pro tier of yno.ai.
    What can Qwen3-Coder do?
    Qwen3-Coder is best for Teams using the original Qwen3-Coder weights or migrating legacy hosted integrations. Its main capabilities include Code, Multilingual Code, Debugging, Refactoring.
    How does Qwen3-Coder compare to other models?
    Qwen3-Coder excels at 480B MoE / 35B active and is recommended for Code generation, Review, Multilingual codebases, East Asian dev teams. See related models below.
    How do I use Qwen3-Coder in yno.ai?
    Sign up for yno.ai, select Qwen3-Coder from the model picker, and start chatting.