Skip to content
LLMs
Mistral AI logo

Mistral: Mistral Small 3

by Mistral AI

Mistral: Mistral Small 3 is a large language model from Mistral AI. It costs $0.050 per million input tokens and $0.080 per million output tokens. Its context window is 33K tokens.

Structured outputOpen weights
Input / 1M tokens
$0.050
Output / 1M tokens
$0.080
Cached input / 1M
-

Not supported

Context window
33K

tokens

Who serves it cheapest

1 hosts serve Mistral Small 3. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Mistral Small 3, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapestfp8$0.050$0.08033K-100.0%

About Mistral Small 3

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

Specifications

Mistral: Mistral Small 3 specifications
Model IDmistralai/mistral-small-24b-instruct-2501
ProviderMistral AI
Context window33K tokens
Max output16K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2023-10-31
Open weightsYes - mistralai/Mistral-Small-24B-Instruct-2501
ReleasedJanuary 30, 2025

Cheaper alternatives

Models that cost less than Mistral Small 3 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Mistral: Mistral Small 3 cost?

$0.050 per million input tokens and $0.080 per million output tokens.

What is the context window of Mistral: Mistral Small 3?

33K tokens, with up to 16K tokens of output per request.

Confirm against the source: Mistral AI official pricing.