mistral-saba
Mistral Saba is a 24B-parameter model designed for the Middle East and South Asia, trained on curated regional data to give accurate, contextually relevant answers.
料金： 入力：100 万トークンあたり 48 クレジット（約 $0.24）、出力：100 万トークンあたり 144 クレジット（約 $0.72）。
料金更新日
今日はどんなお手伝いができますか？
このデモページにはクライアントの完全な記憶機能はありません。すべての機能をご利用いただくには、クライアントまたは CLI から接続してください。
Mistral AI のほかの AI モデル
Saba API on ModelFold
Mistral Saba is a 24B-parameter model designed for the Middle East and South Asia, trained on curated regional data to give accurate, contextually relevant answers. Try Saba in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the Saba API
Saba at a glance
Saba is a chat model from Mistral AI. It accepts text and files (such as PDF) as input and returns text, with a context window of up to 33K tokens.
Use it without hosting anything
On ModelFold you call Saba with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of Saba
Up to 33K tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Understands files (such as PDF)
Besides text, Saba accepts files (such as PDF) as input, so a single request can combine instructions with visual or other media.
Function calling
Saba supports tool (function) calling: describe your functions in the request and the model returns structured calls your code can run — the basis for agents and integrations.
Structured outputs
Ask for JSON that follows a schema (response_format), which makes extraction, classification and system integrations more reliable.
How to Use Saba on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how Saba responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "mistral-saba" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with Saba
Multilingual products
Serve users in many languages with translation, localized support replies and cross-language search.
Writing and content
Draft, edit and translate articles, emails, product copy and documentation in a consistent tone.
High-volume pipelines
Run classification, extraction, rewriting and batch jobs at scale where cost per request matters.
Frequently Asked Questions
What is Saba?⌄
Mistral Saba is a 24B-parameter model designed for the Middle East and South Asia, trained on curated regional data to give accurate, contextually relevant answers.
Which inputs does Saba support?⌄
Saba accepts text and files (such as PDF) and returns text. Through ModelFold you send text messages; documents attached in the Playground are converted to text.
How long is the context window of Saba?⌄
Up to 33K tokens, shared between your input and the model’s output.
Does Saba support function calling?⌄
Yes. Saba supports tools / function calling through the standard tools parameter of the chat completions API.
How is Saba billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call Saba through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "mistral-saba", using your ModelFold API key as the Bearer token.
| 入力 | 48 クレジット 1M tokens≈ $0.24 |
| 出力 | 144 クレジット 1M tokens≈ $0.72 |
トークン単位で課金し、入力と出力は別料金です。思考トークンは出力に含まれます。Playground でも同じ計算を使います。
API ドキュメントを見る →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"mistral-saba","messages":[{"role":"user","content":"Hello"}]}'