AI Model Watch
Models / Mistral

Magistral Small 1.2

Deprecated

Mistral's small multimodal reasoning model (v25.09); alias magistral-small-latest -> magistral-small-2509. Open weights: Apache 2.0, 24B dense (huggingface.co/mistralai/Magistral-Small-2509). Text + image in, reasoning + text out. DEPRECATED 2026-04-30, RETIRES 2026-07-31 -> Mistral Small 4. Lifecycle, price and context from Mistral's official docs model schema; $0.5/M in, $1.50/M out corroborated by mistral.ai/pricing/api. Max output and knowledge cutoff not published -> null.

Magistral Small 1.2 by Mistral costs $0.5 per 1M input tokens and $1.50 per 1M output tokens ($0.75/1M blended), with a 128K (128.000-token) context window. It is deprecated, shutting down 31 Jul 2026; the recommended replacement is Mistral Small 4. Its weights are publicly downloadable, so it can be self-hosted on your own infrastructure.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Lifecycle warning

This model is deprecated. Scheduled shutdown: 31 Jul 2026. Recommended migration: Mistral Small 4.

Read the Magistral Small 1.2 migration guide → replacement & cheapest alternatives

Provider
Mistral
Status
Deprecated
Input price
$0.5 / 1M tokens
Output price
$1.50 / 1M tokens
Cached input
—
Blended price
$0.75 / 1M tokens
Context window
128.000 tokens (128K)
Max output
—
Modality
text, vision
Open weights
Yes — self-hostable
Knowledge cutoff
—
Released
18 Sep 2025
API string
magistral-small-2509

Source: Mistral official documentation ↗

See also

Explore more

All Mistral models→

Prices, context windows and lifecycle status for every Mistral model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Magistral Small 1.2 — questions & answers

How much does Magistral Small 1.2 cost?

Magistral Small 1.2 is priced at $0.5 per 1M input tokens and $1.50 per 1M output tokens ($0.75/1M blended at a 3:1 input-to-output ratio).

What is the context window of Magistral Small 1.2?

Magistral Small 1.2 has a 128.000-token context window (128K).

Is Magistral Small 1.2 being deprecated or retired?

Magistral Small 1.2 is deprecated. Its scheduled shutdown date is 31 Jul 2026. The recommended migration is Mistral Small 4.

Does Magistral Small 1.2 support image or vision input?

Yes — Magistral Small 1.2 accepts image input. Listed modalities: text, vision.

Can I self-host Magistral Small 1.2?

Yes — Magistral Small 1.2 is an open-weight model: its weights are publicly downloadable, so you can run it on your own infrastructure (subject to its license) instead of only calling Mistral's API.

What is the API model string for Magistral Small 1.2?

The API model identifier for Magistral Small 1.2 is "magistral-small-2509" when calling Mistral's API.