Ministral 3 3B Instruct is Mistral AI's language model with a 256K context window and up to 8K output tokens, available from 2 providers, starting at $0.100 / 1M input and $0.100 / 1M output. The instruction-tuned 3B variant of Mistral AI's Ministral 3 family, a tiny yet capable vision-enabled language model.
Specifications
Canonical IDmistral-ministral-3-3b-instruct
TypeLanguage
StatusActive
CreatorMistral AIMistral AI
Providers
Context Window256K tokens
Max Output8K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters3B
Release Date · 6 months ago

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
mistral.ministral-3-3b-instruct
$0.100$0.100$0.050$0.050$0.050$0.050$0.170$0.170
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512
$0.100$0.100
View Amazon Bedrock

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Ministral 3 3B Instruct256K$0.100$0.100Current
Ministral 3 14B Instruct256K$0.200$0.200Available
Ministral 3 8B Instruct256K$0.150$0.150Available

Model IDs