Model prices / Mistral AI / Saba
Saba
Mistral AI · released 2025-02-17
No price from the maker itself is on record for Saba. The lowest of 4 providers is NanoGPT: $0.1989 per 1M input tokens and $0.595 per 1M output tokens (as of 2026-11-12). Context window: 32.8K tokens, up to 26.2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestmistralai/ | $0.1989 | $0.595 | $0.09945 | Lowest | Official docs |
KKilo Gatewaymistralai/ | $0.2 | $0.6 | $0.02 | Official docs | |
 OpenRoutermistralai/ | $0.2 | $0.6 | $0.02 | Official docs | |
 AI/ML APImistralai/ | $0.2116 | $0.6348 | $0.02116 | 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
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Description from models.dev.
Specs
- Type
- Text
- Context
- 32.8K
- Max output
- 26.2K
- Input
- Text, PDF
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2024-09-30
- Open weights
- No
- Released
- 2025-02-17
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.