Skip to content
Models
Stats
Docs
Rewards
Sign in
Get API key
Models
Stats
Docs
Rewards
Status
Sign in
Models
Qwen3 VL 8B Thinking
Qwen
No longer available
Input per 1M
$0.189
Output per 1M
$2.21
Context
131K
tokens
Per 1M tokens
$0.189 · $2.21
Context
131K
tokens
Supports
Reads images
Calls tools
Thinks before it answers
Copy model ID
Pricing and limits
Max output
32,768
tokens
OpenRouter's price plus OpenRouter's 5% platform fee. Deference adds no markup.
More from Qwen
All 46 models
Qwen3.8 Max Prime
$4.20 · $12.60
Reads images
Calls tools
Thinks before it answers
Qwen3.8 Omni Flash
$0.1575 · $0.4935
Reads images
Calls tools
Thinks before it answers
Qwen3.8 Max (0902)
$2.10 · $6.30
Reads images
Calls tools
Thinks before it answers