Model prices / Mistral AI / Mistral Embed
Mistral Embed
Mistral AI · released 2023-12-11
The official API price of Mistral Embed is $0.1 per 1M input tokens and $0 per 1M output tokens (as of 2026-11-12). Context window: 8K tokens, up to 3.1K output tokens per request. 3 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| MistralOfficialmistral-embed | $0.1 | $0 | — | Official | Official docs |
TTempr Gatewaymistral/ | $0.1 | $0 | — | Official docs | |
 Vercel AI Gatewaymistral/ | — | — | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Description from models.dev.
Specs
- Type
- Embedding
- Context
- 8K
- Max output
- 3.1K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- —
- Knowledge cutoff
- —
- Open weights
- No
- Released
- 2023-12-11
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.