Mistral Small 4
Mistral Small 4 is a image-generation model from Mistral, released March 16, 2026. Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
by Mistral · 262K token context window
Best for
- image generation from text
- creative design and ideation
Ways to use Mistral Small 4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Mistral API key. osFoundry discovers Mistral Small 4 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Mistral Small 4 yourself
Mistral Small 4 is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Mistral Small 4 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Mistral Small 4 | Mistral | — | 262K | $ 0.150 /1M | API only |
| GPT-5.4 Mini | OpenAI | — | 400K | $ 0.750 /1M | API only |
| Seed-2.0-Lite | ByteDance Seed | — | 262K | $ 0.250 /1M | API only |
| Qwen3.5-9B | Qwen | — | 262K | $ 0.040 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Mistral Small 4
How much does Mistral Small 4 cost?
Mistral Small 4 is metered at $ 0.150 /1M for input, and $ 0.600 /1M for output. Bring your own Mistral API key — osFoundry passes through provider pricing without markup.
Can I use Mistral Small 4 commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Mistral Small 4?
Mistral Small 4 supports a 262K token context window.
Can I run Mistral Small 4 locally?
No — Mistral Small 4 is hosted only and accessed via the Mistral API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Mistral Small 4 best at?
Mistral Small 4 is well-suited to image generation from text, creative design and ideation.
How do I use Mistral Small 4 in osFoundry?
Paste your Mistral API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral Small 4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Mistral on March 16, 2026. Source: https://openrouter.ai/mistralai/mistral-small-2603