# Qwen3.8 Max 0902 API prices

Qwen3.8 Max 0902 (qwen) — 1.0M context, 131k max output.
8 metered per-token offers from 7 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1.71 | $5.14 | $0.17 | 1.0M |
| Eden AI | $2 | $6 | $0.25 | 1.0M |
| EmpirioLabs AI | $2 | $6 | $2 | 1.0M |
| Kilo Gateway | $2 | $6 | $0.25 | 1.0M |
| NanoGPT | $2 | $6 | $0.17 | 992k |
| Ofox | $2 | $6 | $0.25 | 1.0M |
| OpenRouter | $2 | $6 | $0.25 | 1.0M |
| Vercel AI Gateway | $2 | $6 | $0.25 | 991k |

## Summary

- Cheapest input: $1.71 per 1M tokens (Ofox)
- Cheapest output: $5.14 per 1M tokens (Ofox)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-09-02
- Inputs: image, pdf, text, video

HTML page: https://llmprice.gitlab.io/models/qwen3-8-max-0902/
Full dataset: https://llmprice.gitlab.io/data/catalog.json