Devstral Small

Devstral Small is a text model from Mistral AI with a context window of 256K tokens and max output of 256K tokens. Pricing starts at 0.10 per million input tokens and 0.30 per million output tokens (cheapest at Vercel AI Gateway).

Capabilities

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

Specifications

Model Keymistral/devstral-small-latest
ProviderMistral AI
Provider IDmistral
ModeText
Canonical Namedevstral-small
Context Window256K tokens
Max Output256K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0001000.100
Output Tokens0.0003000.300

Benchmarks

Intelligence Index14.8
Coding Index12.1
Math Index29.3
MMLU-Pro0.6
GPQA0.4
HLE0.0
LiveCodeBench0.3
AIME0.0
IFBench0.3
Time to First Token0.37s
SciCode0.2
MATH-5000.6
AIME 20250.3
LCR0.2
TerminalBench Hard0.1
TAU20.3

Price Comparison by Provider

Compare prices for Devstral Small across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
Vercel AI Gatewayvercel_ai_gateway/mistral/devstral-small0.0700.280
Mistral AImistral/devstral-small-latest0.1000.300

All Variants

All available versions, regions, and API endpoints for Devstral Small.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
mistral/devstral-small-latestMistral AIText0.1000.300256K256Knoyes
vercel_ai_gateway/mistral/devstral-smallVercel AI GatewayText0.0700.280128K128Knoyes