MistralAISeptember 11, 2024

Pixtral 12B

Mistral AI’s 12B open-weight multimodal model, released 2024-09-11; status: deprecated.

Retired · 2025-12-31Text + Image inputText outputOpen weights

At a glance

Context window
128K tokens
Max output
—
Historical text input / output · per 1M tokens
— / —
Knowledge cutoff
—
R.I.P.R.I.P.PixtralPixtral12B12B2024 — 20252024 — 2025MistralAIMistralAIOPEN WEIGHTS LIVE ONOPEN WEIGHTS LIVE ON

A place to remember

Retired, not forgotten.

Released
11 Sep 2024
Endpoint retired
31 Dec 2025
Time in service
476 days

Retired by provider

“Never sat a benchmark. The endpoint is gone. The weights are not.”

The endpoint retired. The open weights can still be run independently; this is not the death of the weights.

0 leaderboards · 0 top-three finishes. The full model record remains below.

Specifications

Provider
MistralAI
Model type
Multimodal model
Released
September 11, 2024
Endpoint retired
2025-12-31 Source
Total parameters
12B
Architecture
Dense
Context window
128K tokens
Input
Text, Image
Output
Text
Weights
Open weights
Licence
Apache 2.0
Commercial use
Commercial use allowed

Model analysis

Pixtral 12B is Mistral AI’s 12B open-weight multimodal model: released 2024-09-11 per the official Mistral model card; API ID pixtral-12b-2409; parameters: 12B; context window 128k; license: Apache 2.0.

Current status: deprecated

The status comes from the lifecycle shown in Mistral Docs. Note: Public announcement article is dated 2024-09-17; release_date follows the model card. This entry is based on the official model page only; independent benchmarks and pricing have not been added.

Source: Mistral official page. Retrieved 2026-10-06.

Last reviewed 2026-10-07

On the stone

Memories and epitaphs, kept separately from model reviews.

Epitaphs from visitors

Nobody has written on this stone yet. The first line is yours.

Write an epitaph

One line for Pixtral 12B. No sign-in, no links, published as written.

8–200 characters200

Community discussion

Share the API, setup, and tradeoffs you actually tested. Rate the model once; comment as often as you like.

Used this model? Sign in with Google to rate it and share what worked, what did not, and which API or setup you tested.

No community comments yet.