Qwen3.8 Max Preview API
About
Build advanced reasoning agents with Qwen3.8 Max Preview, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $1.81/1M input and $5.45/1M output tokens, native tool calling support. Access Qwen3.8 Max Preview via the DevPass (LLM Gateway) API with up to 1.0M output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
Yes
Structured Output
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
1.0M
Tokens
Pricing
Standard (per 1M tokens)
Input
$1.81
Output
$5.45
Caching (per 1M tokens)
Read
$0.21
Write
$2.50
Frequently Asked Questions
Qwen3.8 Max Preview by DevPass (LLM Gateway) costs $1.81 per 1M input tokens and $5.45 per 1M output tokens. Cached reads cost $0.21 per 1M tokens. Cache writes cost $2.50 per 1M tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
LLMGATEWAY_API_KEY
API Base URL
https://api.llmgateway.io/v1