Multilingual text embedding model for retrieval, code search, classification, and clusteringQwen3 Embedding 8B by alibaba is offered by 9 providers on this page. Public prices are shown for 6 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Nebius Token Factory at $0.01 / $0 per 1M. Prices vary about 12× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 40,960 tokens at the reference host, but hosts report different limits, from 32,768 to 40,960, so the usable window depends on the provider you pick. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2025-10.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| InferX Qwen3-Embedding-8B | Gateway | Free | — | — | 32,768 ⚠ | — | ||
| Nebius Token Factory Qwen/Qwen3-Embedding-8B | Cloud | $0.01 | $0 | — | — | 40,960 | — | |
| Hugging Face Qwen/Qwen3-Embedding-8B | Cloud | $0.01 | $0 | — | — | 32,768 ⚠ | — | |
| Novita AI | Gateway | $0.07 | $0 | — | — | 32,768 ⚠ | — | |
| Scaleway | Cloud | $0.11 | $0 | — | — | 32,768 ⚠ | — | |
| Regolo AI | Gateway | $0.10 | $0.10 | — | — | 32,768 ⚠ | 8,192 | |
| evroc Qwen/Qwen3-Embedding-8B | Cloud | $0.12 | $0.12 | — | — | 40,960 | 4,096 | |
| Doubleword Qwen/Qwen3-Embedding-8B | Gateway | — | — | — | — | 32,768 ⚠ | — | hostTable.undisclosed |
| Vercel AI Gateway | Cloud | — | — | — | — | 32,768 ⚠ | — | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (InferX); free tiers usually have rate limits and no SLA, excluded from ranking.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.