Qwen3.8-Max has joined the AIMOWAY model catalog.
The new production model is Qwen’s 2.4-trillion-parameter Mixture-of-Experts flagship, designed for coding, reasoning, data analysis, research, writing, and complex professional workflows.
With a context window approaching one million tokens, it is well suited to tasks involving large codebases, long documents, extensive research material, and multi-step agent workflows.
Transparent Usage-Based Pricing
AIMOWAY currently offers Qwen3.8-Max at:
- Input: $1.90 per 1M tokens
- Output: $5.70 per 1M tokens
- Cached input: $0.239 per 1M tokens
The exact AIMOWAY model ID is:
Qwen3.8-Max
Use It Through an OpenAI-Compatible API
Qwen3.8-Max is available through the same AIMOWAY /v1 endpoint used by the rest of the supported model catalog.
curl https://aimoway.com/v1/chat/completions \
-H "Authorization: Bearer $AIMOWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen3.8-Max",
"messages": [
{
"role": "user",
"content": "Analyze this project and propose the safest implementation plan."
}
]
}'
This makes it possible to evaluate Qwen3.8-Max without adopting a separate SDK or rebuilding an existing OpenAI-compatible integration.
New AIMOWAY accounts include a small starting quota for API testing.
Explore the full model catalog and current pricing:
Read the AIMOWAY documentation:
Top comments (0)