Skip to content
All models

Qwen3 4B

Configuration and per-token prices for this model, as published by /v1/models.

Configuration

Model idboardwalk/qwen3-4b
Hugging Face repoQwen/Qwen3-4B
Pinned revision1cfa9a7208912126459214e8b04321603b3df60c
dtypebfloat16
Quantizationnone
Context length32768 tokens
Enginevllm
Engine versionv0.27.1
Statusactive

Pricing

Input$0.15 per million tokens
Cache read$0.015 per million tokens
Cache write$0.00 per million tokens
Output$0.40 per million tokens