# Qwen3.8 2.4T A95B API prices

Qwen3.8 2.4T A95B (qwen) — 1.0M context, 1.0M max output.
13 metered per-token offers from 12 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $2 | $6 | $0.5 | 262k |
| Deep Infra | $2 | $6 | $0.2 | 262k |
| Eden AI | $2 | $6 | $0.25 | 1.0M |
| Fireworks AI | $2 | $6 | $0.25 | 262k |
| Charm Hyper | $2 | $6 | $0.25 | 1.0M |
| Kilo Gateway | $2 | $6 | $0.25 | 1.0M |
| OpenRouter | $2 | $6 | $0.25 | 1.0M |
| Requesty | $2 | $6 | $0.2 | 262k |
| Vercel AI Gateway | $2 | $6 | $0.25 | 262k |
| Cortecs | $2.5 | $6 | $0.625 | 262k |
| Requesty (eu) | $2.5 | $6 | $0.63 | 1.0M |
| Hugging Face | $2.5 | $6.25 | — | 262k |
| Merge Gateway | $2.5 | $6.25 | $0.5 | 262k |

## Summary

- Cheapest input: $2 per 1M tokens (AIHubMix)
- Cheapest output: $6 per 1M tokens (AIHubMix)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-08-12
- Inputs: image, text

HTML page: https://llmprice.gitlab.io/models/qwen3-8-2-4t-a95b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json