Mistral Saba
Mistral Saba is a language model from Mistral released on Feb 17, 2025. It reads text and writes text, with a 33K token context window and up to 26K tokens per reply.
Show moreShow less
It costs $0.1989 per million input tokens and $0.595 per million output tokens. Cached input bills at $0.0995, 50% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
3 providers serve it, including NanoGPT, Kilo Gateway and AI/ML API.
- Modalities
- In / out price
- $0.1989 / $0.595 per 1M
- Context
- 33K
- Max output
- 26K
- Released
- Feb 17, 2025
- Knowledge cutoff
- Sep 2024
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Mistral Saba pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.1989 / 1M tokens | |
|---|---|---|
| Output | $0.595 / 1M tokens | |
| Cached input (read) | $0.0995 / 1M tokens | 50% off input |
Mistral Saba providers
3 providers serve it, including NanoGPT, Kilo Gateway and AI/ML API. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| NanoGPT | $0.1989 | $0.595 | $0.0995 | 33K | 26K |
| Kilo Gateway | $0.20 | $0.60 | $0.02 | 33K | 26K |
| AI/ML API | $0.2751 | $0.8252 | $0.0275 | 33K | 26K |
What Mistral Saba costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Mistral Saba through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Temperature
temperature
Alternatives to Mistral Saba
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 39.5
Reads text and images. Tool calling, structured output, reasoning. Served by 55 providers.
by deepseekSep 10, 20261M context$0.15/M input tokens$0.60/M output tokens55 providers
- Index 11.3
Reads text and images. Tool calling, structured output, reasoning. Served by 15 providers.
by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens15 providers
- 128K context
Reads text. Tool calling, structured output. Served by 5 providers.
by cohereAug 30, 2024$0.15/M input tokens$0.60/M output tokens5 providers
- Index 11.6
Reads text. Tool calling, structured output, reasoning. Served by 60 providers.
by openaiJan 1, 2024131K context$0.15/M input tokens$0.60/M output tokens60 providers
- Index 25.3
Reads text. Tool calling, structured output, reasoning. Served by 17 providers.
by tencentJul 6, 2026262K context$0.14/M input tokens$0.58/M output tokens17 providers
- Index 41.8
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 65 providers.
by z-aiAug 21, 20261M context$0.15/M input tokens$0.50/M output tokens65 providers
More from Mistral
- Index 38.4
Reads text and images. Tool calling, structured output, reasoning. Served by 8 providers.
by mistralaiOct 6, 20261.05M context$0.68/M input tokens$2.09/M output tokens8 providers
- Index 14.2
Reads text, images and files. Tool calling, structured output, reasoning. Served by 18 providers.
by mistralaiApr 29, 2026262K context$1.50/M input tokens$7.50/M output tokens18 providers
- 262K context
Reads text and images. Tool calling, structured output, reasoning. Served by 5 providers.
by mistralaiApr 29, 2026$1.50/M input tokens$7.50/M output tokens5 providers
- Index 11.3
Reads text and images. Tool calling, structured output, reasoning. Served by 15 providers.
by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens15 providers
- 262K context
Reads text and images. Tool calling, structured output, reasoning. Served by 4 providers.
by mistralaiMar 16, 2026$0.15/M input tokens$0.60/M output tokens4 providers
Voxtral Mini TTS
SpeechTurns text into spoken audio.
by mistralaiMar 1, 2026
Mistral Saba questions
How much does the Mistral Saba API cost?
$0.1989 per million input tokens and $0.595 per million output tokens, with cached input at $0.0995. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Mistral Saba?
32,768 tokens of input, and it can write up to 26,214 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Mistral Saba?
3 providers serve it, including NanoGPT, Kilo Gateway and AI/ML API. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Mistral Saba support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Mistral Saba open source?
No. Mistral serves it through an API only, so you cannot download the weights or host it yourself.
When was Mistral Saba released?
Feb 17, 2025, with training data up to Sep 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Mistral Saba?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting