Mistral: Mistral Saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance.
- Input
- 75,152 Toman/M tokens
- Output
- 218,624 Toman/M tokens
- Context
- 33K
- Max output
- 26K
- Published
- Feb 17, 2025
- Maker
- Mistral
Free plan prices, in Toman at today's rate. Plans and prices
Price by plan
Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period.
| Plan | Input | Output |
|---|---|---|
| Free | 75,152 | 218,624 |
| Pro | 72,072 | 209,664 |
| Max | 68,992 | 200,704 |
Capabilities
- Text
- Tools
- JSON
What it takes and gives
Accepts
- Text
- File (PDF)
Creates
- Text
Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.
Call it
Pass mistralai/mistral-saba as the model name, or let router/auto choose for you.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://ai.fluxcdn.cloud/api/v1",
api_key=os.environ["FLUXCDN_API_KEY"],
)
resp = client.chat.completions.create(
model="router/auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
