Mistral
EfficientAUTO PROFILEPriced via OpenRouter

Saba

text+file->text

Saba is a general-purpose chat-tuned model. Available via Mistral. 32,768-token context. Efficient pricing.

Saba is a efficient AI model from Mistral. It costs $0.2000 per million input tokens and $0.6000 per million output tokens (blended $0.3200/M), with a 32,768-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.2000/M
per million input tokens
OUTPUT
$0.6000/M
per million output tokens
BLENDED 70/30
$0.3200/M
unchanged since 3 May
CONTEXT
32,768
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Solid general chat performance
  • Reasonable instruction following
Typical use cases
  • General chat
  • Drafting and rewriting
  • Personal productivity

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Mistral

See all 15 →

Frequently asked questions

How much does Saba cost?

Saba costs $0.2000 per million input tokens and $0.6000 per million output tokens, for a blended reference rate of $0.3200 per million tokens.

What is Saba's context window?

Saba supports up to 32,768 tokens of context in a single request.

What is Saba best for?

Saba is well suited to Solid general chat performance, Reasonable instruction following and General chat.

Who makes Saba?

Saba is developed and served by Mistral.

Terms used on this page