Mistral AI: Mistral Saba
mistralai/mistral-saba
Try Mistral Saba for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "mistralai/mistral-saba"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "mistralai/mistral-saba"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Mistral Saba is a 24B parameter regional model trained for Arabic and South Asian languages including Tamil and Malayalam. It outperforms models 5x its size on Arabic benchmarks while providing culturally relevant responses.
Context Window 33K
tokens
Max Output 26K
tokens
Input Cost $0.2
per million tokens
Output Cost $0.6
per million tokens
Input text, file
modalities
Tool Use Yes
Release Date Feb 17, 2025
Try Mistral Saba for free
Try Mistral Saba instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Mistral Saba performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 42.4% |
| Humanity's Last Exam Cross-domain reasoning | 4.3% |
| MATH-500 Competition math | 67.7% |
| AIME 2024 Advanced math exam | 13.0% |
Scores sourced from Artificial Analysis.
Find other Mistral AI models →
Mistral Large 4
Mistral Large 4 is a multimodal sparse mixture-of-experts model from Mistral AI with 1 trillion total parameters and 49 billion active. It accepts text and image input and produces text output, and it supports tool calling and structured responses through the API. Mistral positions it for coding, cybersecurity, finance, manufacturing, and visual grounding. In Mistral's preview results it scores 62% on DeepSWE v1.1, 67% on FinWorkBench, and 73% on DIOR-RSVG, and it solves 93% of the 40 Cybench exercises. It is suited to developers building coding agents, security analysis tools, and enterprise workflows that need long context (1M tokens) and image understanding. Open weights are planned for release after the API preview.
ChatMistral Medium 3.5
Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.
ChatMistral Medium 3.5
Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. This entry is Mistral's own dated direct-integration id for the same release available as mistralai/mistral-medium-3-5 through OpenRouter. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.
Frequently Asked Questions
You can access Mistral Saba by Mistral AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Mistral Saba is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Mistral Saba is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.2 |
| Output | $0.6 |
Mistral Saba was created by Mistral AI and released on Feb 17, 2025.
Mistral Saba supports a context window of 33K tokens. For reference, that is roughly equivalent to 66 pages of text.
Mistral Saba can generate up to 26K tokens in a single response.
Mistral Saba accepts the following input types: text, file. It produces: text.
Yes, Mistral Saba supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Mistral Saba scores 6.5 on the Artificial Analysis Intelligence Index, outperforming 17% of tracked models.
Yes — the Mistral Saba API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Mistral Saba to your app for free
Developers can integrate Mistral Saba for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.