Context
128K
Max output
128K
Serving providers
1
Cheapest input
$0.07 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
65 t/s
tokens / second
Time to first token
9.10s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy45.9default
GPQA Diamond41%default
Humanity's Last Exam4%default
IFBench35%default
LiveCodeBench25%default
Long-Context Reasoning17%default
MMLU-Pro62%default
Omniscience-51.1default
SciCode24%default
TerminalBench Hard6%default
τ²-bench28%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Vercel AI GatewayCheapest$0.07$0.281
ComponentUnitStandardBatchCached
Text input/1M tok$0.0700
Text output/1M tok$0.2800

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300Jul 30Jun 22$0.280$0.070

Cost calculator

estimate your monthly spend on this model
$36
estimated / month

Model IDs

copy the exact identifier for your platform
vercel_ai_gateway/mistral/devstral-small

Frequently asked questions

Devstral Small pricing, context and availability

How much does Devstral Small cost?

Devstral Small costs $0.07 per 1M input tokens and $0.28 per 1M output tokens at its cheapest provider via Vercel AI Gateway.

What is the context window of Devstral Small?

Devstral Small accepts up to 128K tokens of context and can return up to 128K output tokens.

What can Devstral Small do?

Devstral Small supports tool use and structured output.

Other Mistral models

compare pricing across the Mistral lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI