Context
128K
Max output
40K
Serving providers
1
Cheapest input
$0.50 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
75 t/s
tokens / second
Time to first token
1.54s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.0 | default | — | |||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 1857.4 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 262.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 66% | default | — | |||||||||||||||||
| Humanity's Last Exam | 6% | default | — | |||||||||||||||||
| IFBench | 44% | default | — | |||||||||||||||||
| LiveCodeBench | 72% | default | — | |||||||||||||||||
| Long-Context Reasoning | 19% | default | — | |||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 77% | default | — | |||||||||||||||||
| MMMU-Pro | 55% | default | — | |||||||||||||||||
| Omniscience | -65.1 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.1 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 35% | — | — | |||||||||||||||||
| TerminalBench Hard | 5% | default | — | |||||||||||||||||
| TerminalBench v2.1 | 4% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 5% | default | — | |||||||||||||||||
| τ²-bench | 28% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Amazon BedrockCheapest | $0.50 | $1.50 | 1 | ||||||||||
Standardmistral.magistral-small-2509
| |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$220
estimated / month
Model IDs
copy the exact identifier for your platformmistral.magistral-small-2509
Frequently asked questions
Magistral Small 2509 pricing, context and availabilityHow much does Magistral Small 2509 cost?
Magistral Small 2509 costs $0.50 per 1M input tokens from Amazon Bedrock, and $1.50 per 1M output tokens from 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 40K output tokens.
What can Magistral Small 2509 do?
Magistral Small 2509 supports image input (vision), tool use, reasoning and structured output.
Other Mistral models
compare pricing across the Mistral lineupMixtral 8x7B Instruct V0.1$0.15/1M · 7 providersMistral Nemo Instruct 2407$0.019/1M · 5 providersMistral Nemo$0.029/1M · 5 providersMistral Large$2.00/1M · 5 providersMistral Large 2407$2.00/1M · 5 providersMistral 7B Instruct V0.2$0.05/1M · 4 providersMistral Small 3$0.05/1M · 4 providersMistral 7B Instruct V0.1$0.15/1M · 4 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI