Magistral Small 1.2 is the September 2025 update to Mistral's 24B-parameter open-source reasoning model, adding multimodal vision to the original Magistral Small. It keeps strong mathematical and logical reasoning while introducing image understanding, with Mistral reporting gains over the June 2025 release on math and coding benchmarks. The model combines transparent, interpretable multi-step reasoning with vision input, enabling applications that need both visual analysis and complex logical thinking. With a 128k token context window and Apache 2.0 licensing, Magistral Small 1.2 is fully open-weight and suited to self-deployment across diverse hardware. Built for professional domains that require reasoning alongside visual understanding, it supports multilingual chains of thought while staying compact enough to run locally. It succeeds the June 2025 Magistral Small 1.0, adding vision inputs and improved reasoning.
Magistral Small 1.2 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance β full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Mistral | EU | Enterprise | No | $0.50 | $1.50 |
Training posture across routes: No training on prompts by default.
Each route hosting Magistral Small 1.2 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Magistral Small 1.2 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent β Claude Code, Cursor, Codex, and more β and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "mistral/magistral-small-2509",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
