Qwen3 Embedding 8B: API pricing, providers and specs
Qwen3 Embedding 8B is a embedding model by Alibaba. 5 providers serve it, from $0.039 to $0.039 /1M; the lowest price is at SiliconFlow.
How Qwen3 Embedding 8B compares
Against the 15 embedding models on the site priced the same way.
- Mid-priced: its lowest price is $0.039 /1M against a median of $0.059; 44% of comparable models cost less.
- Its 33K-token context window is larger than 67% of them (median 8K), about 50 pages of text.
- 5 providers serve it; 63% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Qwen3 Embedding 8B prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| $0.068/1M | Free/1M | — | — | |
| DevPass (LLM Gateway) | $0.01/1M | FromFree/1M | — | — |
FastRouter | $0.01/1M | Free/1M | — | 33K |
Impossibl | $0.10/1M | Free/1M | — | — |
| — | $0.039/1M | — | — |
Specs
- Type
- Embedding
- Maker
- Alibaba
- Inputs
- Text
- Outputs
- Text
- Context
- 33K≈ 50 pages of text
- Max output
- 33K
- Capabilities
- —
- Released
- Jun 3, 2025
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 7.6B
Alternatives to Qwen3 Embedding 8B
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| $0.039/1M | 33K | — | 5 | |
| Bge Large En V1.5 | $0.034/1M | — | — | 1 |
| Bge Large Zh V1.5 | $0.034/1M | — | — | 1 |
| $0.10/1M | — | — | 1 | |
| $0.02/1M | — | — | 1 | |
| Text Embedding 3 Large | $0.104/1M | 8K | — | 13 |
| Text Embedding 3 Small | $0.016/1M | 8K | — | 13 |
| Text Embedding Ada 002 | $0.08/1M | 8K | — | 9 |
More from Alibaba
Qwen3 Embedding 8B FAQ
The lowest price for Qwen3 Embedding 8B is $0.039 /1M, at SiliconFlow.
SiliconFlow, at $0.039 /1M. 5 providers serve Qwen3 Embedding 8B; the table above lists every one with its price.
Qwen3 Embedding 8B reads up to 33K tokens per request and writes up to 33K.
Yes. Qwen3 Embedding 8B's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 7.6B, as the safetensors metadata of its official Hugging Face repo states.
5 API providers serve Qwen3 Embedding 8B. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us

