Mistral AI logo

Mistral: Saba

mistralai/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. Trained on curated regional...

Modalities

TextFiles / PDFText

In / out price

$0.2 / $0.6 per 1M

Context

33K

Released

Feb 17, 2025

Why use Saba

  • Reads PDFs and other files
  • Tool and function calling (agent-ready)
  • Structured (JSON) outputs

Pricing

Input$0.2 / 1M tokens
Output$0.6 / 1M tokens
Cached input (read)$0.020 / 1M tokens

List prices via OpenRouter, checked daily. Real cost depends on the provider and on reasoning tokens.

Cost calculator

Pick a task, set how often you run it, and compare what it costs on each model.

ModelPer runPer monthPer 1,000 runs
Mistral: Saba$0.0014$1.36$1.36

Estimates from list prices via OpenRouter; real bills vary by provider and reasoning tokens.

Will it fit? Context window simulator

Each square is about one page (500 words). Colored squares are your content; grey squares are free space in the model's context window.

Your content

  • Novel (90,000 words)

Total: about 120,000 tokens (≈ 90,226 words). Token counts are estimates.

Models

Mistral: Saba

32,768 tokens ≈ 50 pages

Does not fit: needs 3.7× the window. The oldest 73% would be cut off.

Write with the best model for the job

WordGPT picks and switches models for you: drafting, editing and files in one place. Free plan, no credit card.

Try it free

More from Mistral AI