Models / Qwen
Code
Chat

Qwen2.5 Coder 32B Instruct

SOTA code LLM with advanced code generation, reasoning, fixing, and support for up to 128K tokens.

Try now
read docs

About model

Qwen2.5 Coder 32B Instruct generates and reasons about code, excelling in code generation, fixing, and reasoning, making it suitable for developers and applications like Code Agents.

    Related models
    new
    Chat
    DeepSeek V4 Pro

    • Cached/1M

      $0.20

    • Input/1M

      $1.74

    • Output/1M

      $3.48
    Function Calling
    JSON Mode
    Reasoning
    Chat
    Code
    LLM
    Black stylized letter P with a semicircle shape on the left side on white background.
    Chat
    Gemma-4-31B-it-Pearl

    • Input/1M

      $0.28

    • Output/1M

      $0.86
    • Parameters
      31B
    Function Calling
    JSON Mode
    Reasoning
    Chat
    LLM
    new
    Chat
    Qwen3.7-Max

    • Cached/1M

      $0.13

    • Input/1M

      $1.25

    • Output/1M

      $3.75
    Function Calling
    JSON Mode
    Reasoning
    Chat
    Code
    LLM
    Model specifications
    Model data
    • Model provider
      Qwen
    • Type
      Code
      Chat
    • Main use cases
      Chat
      Coding Agents
      Small & Fast
    • Features
      JSON Mode
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      32.8B
    • Context length
      32768
    • Input price

      $0.80 / 1M tokens

    • Output price

      $0.80 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Text
    • Released
      November 5, 2024
    • Quantization level
      FP16
    • External link
      Provider docs
    • Category
      Chat
    Quickstart docs
    Deploy model