mistralai

Mistral: Saba

The Mistral: Saba is an AI model that can process text and file inputs within a context length of 32,768 tokens. It supports tools, but not reasoning or structured output. Users can input files in addition to text. For those who need to process large amounts of data without breaking the bank, the Mistral: Saba might be worth considering due to its competitive price point of $0.2 per million input tokens and $0.6 per million output tokens. However, its blended benchmark score of 8.7 is based on a relatively low coverage of one independent benchmark, leaving room for further evaluation before making a decision.

Quality Score
78/100
price + capability + benchmarks
Input Price
$0.20
per 1M tokens · checked 2026-09-04
Output Price
$0.60
per 1M tokens · checked 2026-09-04
Context Window
32,768
tokens

Benchmark results

Independent, published benchmarks. Blended score 8.7 across 1 benchmark, last refreshed 2026-09-04. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 10.2
Model ID
mistralai/mistral-saba
Vendor
mistralai
Released
February 2025
Tokenizer
Mistral
Input Modalities
text, file
Output Modalities
text
Max Output
26,214 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.20/M input and $0.60/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.13
A month of a busy support chatbot 5M in / 2M out $2.20

Similar models

Quick answers

How much does Mistral: Saba cost?
$0.20 per million input tokens and $0.60 per million output tokens.
What is Mistral: Saba's context window?
32,768 tokens, roughly 49 pages of text in a single request.
Does Mistral: Saba support tool calling?
It supports tool calling, structured output.
Can Mistral: Saba process images?
No, it is text-only on the input side.