Mistral AI logo

Mistral AI: Magistral Small 1.2

Open multimodal reasoning model for transparent analysis of text and images

Source-linked magistral Open weights Apache 2.0 Released 2025-09-18
API record Report
InputT
OutputT
Input price$0.5/M
Output price$1.5/M
Context131.072K
Max output131.072K
Providers1
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Magistral Small 1.2
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Amazon Bedrock mistral.magistral-small-2509 128K 40K $0.5 $1.5 ReasoningToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.5/M

Across 1 priced provider

Median input $0.5/M

Midpoint of listed rates

Highest input $0.5/M

Same as the lowest listed rate

Output range $1.5 – $1.5

Per million output tokens

Amazon Bedrock $0.5/MLowest
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.
Specification

Capabilities

Recorded from the source catalog and provider listings.

Reasoning Yes
Tool calling Yes
Structured output Yes
Attachments Yes
Vision input Yes
Open weights Yes
Creator
Mistral AI
Model family
magistral
Knowledge cutoff
Not documented
License
Apache 2.0
Release date
2025-09-18
Model ID
mistral/magistral-small-2509

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/mistral/magistral-small-2509
curl
curl "https://model.kyssta.lol/api/v1/models/mistral/magistral-small-2509"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Magistral Small 1.2?

Open multimodal reasoning model for transparent analysis of text and images. It is published by Mistral AI and catalogued here from Models.dev.

How much does Magistral Small 1.2 cost?

Listed input pricing starts at $0.5 per million tokens from Amazon Bedrock.

What is the context length of Magistral Small 1.2?

Magistral Small 1.2 accepts up to 131.072K tokens of context and returns up to 131.072K output tokens.

Does Magistral Small 1.2 support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve Magistral Small 1.2?

1 provider list this model: Amazon Bedrock.

Are the weights for Magistral Small 1.2 open?

Yes. The weights are published and downloadable from Hugging Face under the Apache 2.0 license.

When was Magistral Small 1.2 released?

The catalog records a release date of 2025-09-18, last verified Sep 12, 2026.

More models from Mistral AI

View all →