Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Qwen 3 Embedding 4B by alibaba is offered by 4 providers on this page. Public prices are shown for 3 of them. Its reference price is $0.15 per 1M input tokens and $0 per 1M output tokens. The lowest paid channel is Inference at $0.01 / $0 per 1M, about 15× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 32,000 tokens at the reference host, but hosts report different limits, from 32,000 to 32,768, 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. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-12.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Inference | Gateway | $0.01 | $0 | — | — | 32,000 | 2,048 | |
| Hugging Face Qwen/Qwen3-Embedding-4B | Cloud | $0.01 | $0 | — | — | 32,000 | 2,048 | |
| Privatemode AI | Gateway | $0.15 | $0 | — | — | 32,000 | 2,560 | |
| Vercel AI Gateway | Cloud | — | — | — | — | 32,768 ⚠ | 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.