Back to Models

Qwen: Qwen-Max

qwen/qwen-max
Feb 1, 202532.8K context8.2K max output$1.60/M in · $6.40/M out

Description

Qwen-Max, based on Qwen2.5, provides the best inference performance among Qwen models, especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion tokens and further post-trained with curated Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) methodologies. The parameter count is unknown.

Specifications

Provider
qwen
Context Length
32.8K
Max Output
8.2K
Modality
Intext
Outtext

Pricing

TypePrice / 1M tokens
Input$1.60
Output$6.40
Cache Read$0.32

Quick Start

curl https://api.ominigate.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen-max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'