# Qwen3.5 4B API prices

Qwen3.5 4B (qwen) — 262k context, 33k max output.
2 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| EmpirioLabs AI | $0.04 | $0.07 | $0.02 | 262k |
| NanoGPT | $0.1 | $0.2 | $0.05 | 262k |

## Summary

- Cheapest input: $0.04 per 1M tokens (EmpirioLabs AI)
- Cheapest output: $0.07 per 1M tokens (EmpirioLabs AI)
- First-party: not listed separately
- Free offers: QVAC
- Subscription plans (not per-token): none
- Released: 2025-11-01
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/qwen3-5-4b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json