Models›Mistral

Mistral

French lab shipping efficient open-weight and commercial models known for strong performance per parameter.

Models
17
on Gizmo
Free
0
plan limits apply
Open weights
9
downloadable
Largest context
262k
tokens

Models · 17

Compare Fast and Cheap modes, see the percentage saved, or filter to models with a verified discount. Select any model for its full pricing and API options.

Fast mode prioritizes response speed. Cheap mode uses lower-cost capacity and may be a little slower. Compare the same model’s input and output rates below.

ModelFast mode Input / output per 1M tokensCheap mode Input / output per 1M tokensDiscountRun model
Mistral Medium 3.5Mistral · 262K context$1.575 / $7.875No verified discount—
Mistral Medium 3.5 (batch)Mistral · 262K context$0.7875 / $3.9375No verified discount—
Mistral Small 4Mistral · 262K context$0.1575 / $0.63No verified discount—
Ministral 3 14B 2512Mistral · 262K context$0.21 / $0.21No verified discount—
Ministral 3 8B 2512Mistral · 262K context$0.1575 / $0.1575No verified discount—
Ministral 3 3B 2512Mistral · 131K context$0.105 / $0.105No verified discount—
Voxtral Small 24B 2507Mistral · 33K context$0.105 / $0.315No verified discount—
Mistral Medium 3.1Mistral · 131K context$0.42 / $2.1No verified discount—
Codestral 2508Mistral · 256K context$0.315 / $0.945No verified discount—
Mistral Small 3.2 24BMistral · 256K context$0.0788 / $0.21No verified discount—
Mistral Medium 3Mistral · 131K context$0.42 / $2.1No verified discount—
SabaMistral · 33K context$0.21 / $0.63No verified discount—
Mistral Small 3Mistral · 33K context$0.0525 / $0.084No verified discount—
Mistral Large 2407Mistral · 131K context$2.1 / $6.3No verified discount—
Mistral NemoMistral · 131K context$0.0305 / $0.0315$0.0174 / $0.022728–42.9% off
Mixtral 8x22B InstructMistral · 66K context$2.1 / $6.3No verified discount—
Mistral LargeMistral · 128K context$2.1 / $6.3No verified discount—
17 of 17 models · Prices include your 5% platform fee.

Discounts compare current uncached input and output rates. Different percentages mean savings depend on your token mix. Fast rates are routing ceilings; actual charges and capacity may vary. No discount is shown without a verified quote.