Context
128K
Max output
8K
Serving providers
1
Cheapest input
$0.50 /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
66 t/s
tokens / second
Time to first token
7.75s
latency
Headline indices
14.7
of 100
1.4
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy3136.5default
GDPval248.4default
GPQA Diamond66%default
Humanity's Last Exam6%default
IFBench44%default
LiveCodeBench72%default
Long-Context Reasoning16%default
MMLU-Pro77%default
MMMU-Pro55%default
Omniscience-65.0default
SciCode35%default
TerminalBench Hard5%default
TerminalBench v2.14%default
τ-bench Banking4%default
τ²-bench28%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon BedrockCheapest$0.50$1.501
ComponentUnitStandardBatchCached
Text input/1M tok$0.5000
Text output/1M tok$1.50

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50Dec 8Jun 22$1.50$0.500

Cost calculator

estimate your monthly spend on this model
$220
estimated / month

Model IDs

copy the exact identifier for your platform
mistral.magistral-small-2509

Frequently asked questions

Magistral Small 2509 pricing, context and availability

How much does Magistral Small 2509 cost?

Magistral Small 2509 costs $0.50 per 1M input tokens and $1.50 per 1M output tokens at its cheapest provider via Amazon Bedrock.

What is the context window of Magistral Small 2509?

Magistral Small 2509 accepts up to 128K tokens of context and can return up to 8K output tokens.

What can Magistral Small 2509 do?

Magistral Small 2509 supports tool use and reasoning.

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