Description
Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), 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.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Qwen: Qwen-Max (qwen/qwen-max)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "qwen/qwen-max",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Qwen: Qwen-Max model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 1.6$ / 1M tokens
- Output: 6.4$ / 1M tokens
Token Limits
- Max Output: 8,192 tokens
- Max Context: 32,768 tokens
Subscription Tiers
- free
- pro
- ultimate