modelbenchmark.io

Mistral Small (latest)

Mistral · mistral-small

Compare

Efficient Mistral model for fast chat, extraction, and production assistants

Specification

mistral listing

Context
262K
Max output
256K
Released
2026-03-16
Knowledge cutoff
2025-06
Retires
2025-07-31
Open weights
yes
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.15
Output
$0.60
Cache read
$0.015

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock$0.50
Batch outputbedrock$1.50

Batch input is 50% below the interactive input price at the same listing.

Available from 24 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor
$0.15
$0.10
$0.60
$0.30
$0.015
$0.01
—
262K
128K
32K
256K
16K
8K
262K
—
helicone$0.075$0.20——128K16K—
azure$0.10$0.30——128K33K—
azure-cognitive-services$0.10$0.30——128K33K—
google-vertex$0.10$0.30——128K16K—
vercel_ai_gateway · vercel-ai-gateway$0.10$0.30——32K4K—
vertex_ai-mistral_models$0.10$0.30——128K128K—
watsonx$0.10$0.30——32K32K—
edenai$0.15$0.60$0.015—262K256K—
kilo$0.15$0.60$0.015—262K210K—
llmgateway
$0.15
$0.10
$0.60
$0.30
——
262K
128K
256K
16K
—
llmgateway-providers
$0.15
$0.10
$0.60
$0.30
——
262K
128K
256K
16K
—
merge-gateway$0.15$0.60——256K256K—
openrouter$0.15$0.60$0.015—262K210K—
tempr$0.15$0.60$0.015—256K256K—
vercel$0.15$0.60$0.015—262K4K—
cortecs
$0.156
$0.111
$0.625
$0.334
$0.016—
262K
128K
256K
128K
—
lowrouter · auto$0.1569$0.6275$0.0157—256K256K—
prime$0.165$0.66——262K210K—
requesty$0.165$0.66$0.165—256K256K—
aimlapi$0.1984$0.7935$0.0159—262K256K—
opper$0.5811$2.4406——256K8K—
azure_ai
$1.00
$0.10
$3.00
$0.30
——
32K
128K
8K
128K
2025-07-31
2027-02-15
bedrock$1.00$3.00——32K4K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02cortecsCache read$0.014
2026-09-15cortecsCache read$0.016
2026-09-02mistralCache read$0.015
2026-09-18mistralCache read$0.01
2026-09-29mistralCache read$0.015
2026-09-02openrouterCache read$0.015
2026-09-06openrouterCache read$0.015
2026-10-10openrouterCache read$0.015
2026-09-02cortecsInput$0.143
2026-09-04cortecsInput$0.111
2026-09-15cortecsInput$0.111
2026-09-24cortecsInput$0.156
2026-10-19cortecsInput$0.111
2026-10-20cortecsInput$0.156
2026-10-21cortecsInput$0.111
2026-10-23cortecsInput$0.156
2026-10-24cortecsInput$0.111
2026-10-25cortecsInput$0.156
2026-10-26cortecsInput$0.111
2026-10-27cortecsInput$0.156
2026-10-30cortecsInput$0.111
2026-11-01cortecsInput$0.156
2026-09-02llmgatewayInput$0.10
2026-09-28llmgatewayInput$0.15
2026-10-19llmgatewayInput$0.10
2026-10-20llmgatewayInput$0.15
2026-10-24llmgatewayInput$0.10
2026-10-25llmgatewayInput$0.15
2026-10-27llmgatewayInput$0.10
2026-10-30llmgatewayInput$0.15
2026-10-31llmgatewayInput$0.10
2026-11-01llmgatewayInput$0.15
2026-09-02llmgateway-providersInput$0.10
2026-09-28llmgateway-providersInput$0.15
2026-10-19llmgateway-providersInput$0.10
2026-10-20llmgateway-providersInput$0.15
2026-10-24llmgateway-providersInput$0.10
2026-10-25llmgateway-providersInput$0.15
2026-10-27llmgateway-providersInput$0.10
2026-10-30llmgateway-providersInput$0.15
2026-10-31llmgateway-providersInput$0.10
2026-11-01llmgateway-providersInput$0.15
2026-09-02mistralInput$0.15
2026-09-04mistralInput$0.10
2026-09-24mistralInput$0.15
2026-10-19mistralInput$0.10
2026-10-20mistralInput$0.15
2026-10-27mistralInput$0.10
2026-10-28mistralInput$0.15
2026-10-29mistralInput$0.10
2026-10-30mistralInput$0.15
2026-10-31mistralInput$0.10
2026-11-01mistralInput$0.15
2026-09-02openrouterInput$0.15
2026-09-06openrouterInput$0.15
2026-10-10openrouterInput$0.15
2026-09-02opperInput$0.15
2026-09-22opperInput$0.5811
2026-09-02vercelInput$0.10
2026-09-16vercelInput$0.15
2026-09-02vertex_ai-mistral_modelsInput$1.00
2026-09-13vertex_ai-mistral_modelsInput$0.10
2026-09-02cortecsOutput$0.568
2026-09-04cortecsOutput$0.334
2026-09-15cortecsOutput$0.334
2026-09-24cortecsOutput$0.625
2026-10-19cortecsOutput$0.334
2026-10-20cortecsOutput$0.625
2026-10-21cortecsOutput$0.334
2026-10-23cortecsOutput$0.625
2026-10-24cortecsOutput$0.334
2026-10-25cortecsOutput$0.625
2026-10-26cortecsOutput$0.334
2026-10-27cortecsOutput$0.625
2026-10-30cortecsOutput$0.334
2026-11-01cortecsOutput$0.625
2026-09-02llmgatewayOutput$0.30
2026-09-28llmgatewayOutput$0.60
2026-10-19llmgatewayOutput$0.30
2026-10-20llmgatewayOutput$0.60
2026-10-24llmgatewayOutput$0.30
2026-10-25llmgatewayOutput$0.60
2026-10-27llmgatewayOutput$0.30
2026-10-30llmgatewayOutput$0.60
2026-10-31llmgatewayOutput$0.30
2026-11-01llmgatewayOutput$0.60
2026-09-02llmgateway-providersOutput$0.30
2026-09-28llmgateway-providersOutput$0.60
2026-10-19llmgateway-providersOutput$0.30
2026-10-20llmgateway-providersOutput$0.60
2026-10-24llmgateway-providersOutput$0.30
2026-10-25llmgateway-providersOutput$0.60
2026-10-27llmgateway-providersOutput$0.30
2026-10-30llmgateway-providersOutput$0.60
2026-10-31llmgateway-providersOutput$0.30
2026-11-01llmgateway-providersOutput$0.60
2026-09-02mistralOutput$0.60
2026-09-04mistralOutput$0.30
2026-09-24mistralOutput$0.60
2026-10-19mistralOutput$0.30
2026-10-20mistralOutput$0.60
2026-10-27mistralOutput$0.30
2026-10-28mistralOutput$0.60
2026-10-29mistralOutput$0.30
2026-10-30mistralOutput$0.60
2026-10-31mistralOutput$0.30
2026-11-01mistralOutput$0.60
2026-09-02openrouterOutput$0.60
2026-09-06openrouterOutput$0.60
2026-10-10openrouterOutput$0.60
2026-09-02opperOutput$0.60
2026-09-22opperOutput$2.4406
2026-09-02vercelOutput$0.30
2026-09-16vercelOutput$0.60
2026-09-02vertex_ai-mistral_modelsOutput$3.00
2026-09-13vertex_ai-mistral_modelsOutput$0.30
2026-10-13aimlapiCache read$0.0206
2026-10-23aimlapiCache read$0.0159
2026-10-13aimlapiInput$0.2579
2026-10-23aimlapiInput$0.1984
2026-10-13aimlapiOutput$1.0315
2026-10-23aimlapiOutput$0.7935

More from Mistral

most-hosted first