Skip to content
LLMs
Mistral AI logo

Mistral: Mistral Small 3.1 24B

by Mistral AI

Mistral: Mistral Small 3.1 24B is a large language model from Mistral AI. It costs $0.351 per million input tokens and $0.555 per million output tokens. Its context window is 128K tokens.

Open weightsimage input
Input / 1M tokens
$0.351
Output / 1M tokens
$0.555
Cached input / 1M
-

Not supported

Context window
128K

tokens

Who serves it cheapest

1 hosts serve Mistral Small 3.1 24B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Mistral Small 3.1 24B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
CloudflareCheapest$0.351$0.555128K-100.0%

About Mistral Small 3.1 24B

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

Specifications

Mistral: Mistral Small 3.1 24B specifications
Model IDmistralai/mistral-small-3.1-24b-instruct
ProviderMistral AI
Context window128K tokens
Max output102K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff2023-10-31
Open weightsYes - mistralai/Mistral-Small-3.1-24B-Instruct-2503
ReleasedMarch 17, 2025

Cheaper alternatives

Models that cost less than Mistral Small 3.1 24B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Mistral: Mistral Small 3.1 24B cost?

$0.351 per million input tokens and $0.555 per million output tokens.

What is the context window of Mistral: Mistral Small 3.1 24B?

128K tokens, with up to 102K tokens of output per request.

Confirm against the source: Mistral AI official pricing.