LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Magistral Small 1.2

mistral·mistral/magistral-small-2509·GA·Open weights·magistral series
Open multimodal reasoning model for transparent analysis of text and images

Magistral Small 1.2 by mistral is currently listed from a single provider. Its reference price is $0.50 per 1M input tokens and $1.50 per 1M output tokens.

Artificial Analysis rates it 8.6 on the Intelligence Index, with 14.7 for coding. Against its lowest blended price of $0.75 per 1M, that is roughly 11 index points per dollar, which is the value ratio the leaderboards rank on.

The context window is 128,000 tokens, with an output limit of 40,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Specs & pricing

Input / output per 1M tokens
Reference price·Amazon Bedrock
$0.50 / $1.50
Blended $0.75 · Cache read —
Lowest paid·Amazon BedrockCloud
$0.50 / $1.50
Blended $0.75
Context
128,000
Output limit
40,000
Knowledge cutoff
—
Released / updated
2025-09-18 / 2025-09-18
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImage
License
Apache-2.0
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence8.6
Value11
Coding14.7
Agentic—
Output speed—
TTFT—
Value formulaIQ 8.6 ÷ min blended $0.750 = 11

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Amazon Bedrock
mistral.magistral-small-2509
Cloud$0.50$1.50——128,00040,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Upstream provides no control info

1 / 1 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1Amazon Bedrock$175.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.50Output list $1.50Min blended $0.75

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-12). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations11 items

GPQA Diamond66.3%
Humanity's Last Exam6.4%
MMLU-Pro76.8%
LiveCodeBench72.3%
Terminal-Bench Hard4.5%
Terminal-Bench 2.14.5%
AIME 202580.3%
τ²-Bench Telecom27.8%
τ³-Bench Banking4.5%
AA-LCR19.3%
IFBench44.4%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Magistral Smallsame series$0.50 / $1.50DeepSeek V4 Flashcheaper alternative$0.15 / $0.60GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flashcheaper alternative$0.15 / $0.60GPT-5 Nanocheaper alternative$0.05 / $0.40
Data partly from models.dev (MIT) · Amazon Bedrock official docs ↗