Mistral AI · Released Feb 17, 2025Saba
Mistral model for multilingual chat, reasoning, and tool-assisted workflows.
- Capability
- —No ECI score yet
- Input
- $0.20per 1M tokens
- Output
- $0.60per 1M tokens
- Context
- 33K26K max output
What it costs
- Input
- $0.20per million tokens
- Output
- $0.60per million tokens
- Blended (3:1)
- $0.30cheaper than 69% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.70 |
| Team assistant25M input + 5M output tokens | $8.00 |
| Production app250M input + 50M output tokens | $80.00 |
Median of 4 paid API providers on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Saba yet.
The details
- Lab
- Mistral AI
- Released
- Feb 17, 2025
- Knowledge cutoff
- Sep 30, 2024
- Context window
- 32,768 tokens
- Max output
- 26,214 tokens
- Inputs
- Text, PDFs
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Proprietary
- Availability
- 4 API providerslisted on models.dev
More from Mistral AI
About Saba
How much does Saba cost?
Saba costs $0.20 input / $0.60 output per million tokens (median across 4 API providers). At a 3:1 input-to-output mix that is $0.30 per million tokens, cheaper than 69% of the 445 priced models we track.
What is the context window of Saba?
Saba accepts up to 32,768 tokens per request and can write up to 26,214 tokens in one response.
How good is Saba?
Epoch AI has not published a Capabilities Index score for Saba yet.
Is Saba open source?
No. Saba is proprietary; you use it through an API or partner platforms.
What inputs does Saba support?
Saba accepts text and PDFs and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Saba released?
Mistral AI released Saba on Feb 17, 2025. Its training data runs to Sep 30, 2024.
What are the best alternatives to Saba?
The closest current models from other labs on capability, price and release date are Solar Pro 2 (Upstage, $0.25 / $0.25), Command R (Cohere, $0.15 / $0.60), Llama 3.3 Nemotron Super 49B v1 (NVIDIA, $0.15 / $0.15) and Phi-4-mini (Microsoft, $0.075 / $0.30).