Mistral: Saba

Public pricingIntelligence 79/100Medium memoryツール利用

Mistral: Saba は テキスト モデルで、汎用チャット、分析、業務利用 に向いています。低遅延で効率的な推論、33K tokensのコンテキスト、低コストの特性を組み合わせ、general chat, analysis, and production workloads で安定した動作を支えます。遅延・コスト・スループット が重要な場面に合っており、安定した出力、柔軟な導入、拡張性を求めるチームに実用的です。 安定した応答、長い文脈処理、そして試作から本番まで広く使える柔軟さが必要な場面で役立ちます。 安定した応答、長い文脈処理、そして試作から本番まで広く使える柔軟さが必要な場面で役立ちます。 安定した応答、長い文脈処理、そして試作から本番まで広く使える柔軟さが必要な場面で役立ちます。

Input

$0.20/1M

Output

$0.60/1M

Cached

$0.02/1M

Batch

$0.10/1M

Calculate your Saba bill.

Set your workload — see cost at your exact volume.

What would Saba cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Saba at a glance.

Memory

32,768

tokens

Max reply

8,192

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

mistral

Released

Feb 2025

Training cutoff

Oct 2024

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Saba

  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Saba — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Saba costs roughly $39 per month. Input is $0.20 /1M tokens and output is $0.60 /1M tokens.
Saba has a 32,768-token context window (medium memory — a long report or a codebase file). That means you can fit about 6,144 words of input and history in a single call.
Beyond text generation, Saba supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Saba was released in February 2025, with training data cut off around October 2024.
Models in a similar class include Ministral 3 14B 2512, Ministral 3 8B 2512, Mistral Small 4. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Saba against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard