Mistral.Ministral 3 8 b Instruct Pricing & Specs | AI Models

Ministral 3 8B Instruct is a text model from AWS Bedrock with a context window of 128K tokens and max output of 8K tokens. Pricing starts at 0.15 per million input tokens and 0.15 per million output tokens (cheapest at AWS Bedrock).

Capabilities

✗ Vision✓ Function Calling✗ Reasoning✗ JSON Schema✓ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output

Specifications

Model Key	`mistral.ministral-3-8b-instruct`
Provider	AWS Bedrock
Provider ID	bedrock_converse
Mode	Text
Canonical Name	ministral-3-8b
Context Window	128K tokens
Max Output	8K tokens

Pricing

Type	Per 1K Tokens	Per 1M Tokens
Input Tokens	0.000150	0.150
Output Tokens	0.000150	0.150

Benchmarks

Intelligence Index	14.8#133
Coding Index	10.0#135
Math Index	31.7#79
MMLU-Pro	0.6#136
GPQA	0.5#145
HLE	0.0#151
LiveCodeBench	0.3#108
IFBench	0.3#144
Time to First Token	0.30s#85
SciCode	0.2#157
AIME 2025	0.3#79
LCR	0.2#94
TerminalBench Hard	0.0#107
TAU2	0.3#94

Price Comparison by Provider

Compare prices for Ministral 3 8B Instruct across different providers. The same model may be available through multiple providers at different price points.

Provider	Model Key	Input Price, $	Output Price, $
OpenRouter	openrouter/mistralai/ministral-8b-2512	0.150	0.150
AWS Bedrock	mistral.ministral-3-8b-instruct	0.150	0.150

All Variants

All available versions, regions, and API endpoints for Ministral 3 8B Instruct.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
mistral.ministral-3-8b-instruct	AWS Bedrock	Text	0.150	0.150	128K	8K	no	yes
openrouter/mistralai/ministral-8b-2512	OpenRouter	Text	0.150	0.150	262K	262K	yes	yes

← Back to All Models