# Qwen3 Embedding 8B API prices

Qwen3 Embedding 8B (qwen) — 41k context, 33k max output.
2 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Regolo AI | $0.1 | $0.1 | — | 33k |
| evroc | $0.115 | $0.115 | — | 41k |

## Summary

- Cheapest input: $0.1 per 1M tokens (Regolo AI)
- Cheapest output: $0.1 per 1M tokens (Regolo AI)
- First-party: not listed separately
- Free offers: InferX
- Subscription plans (not per-token): none
- Released: 2025-06-05
- Inputs: text

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