Mistral-Nemo-Instruct-2407

apache-2.0

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Context
131K
Input price
$0.03/1M tokens
Output price
$0.03/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDmistralai/Mistral-Nemo-Instruct-2407
Provider DeepInfra
Creator Mistral AI
Familymistral
Licenseapache-2.0
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window131K tokens
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.03
Output
$0.03
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: mistral

ModelContextMax outPricing
Mistral-Nemo-Instruct-2407131K—$0.03$0.03
Mistral-Small-24B-Instruct-250133K—$0.05$0.08
Mistral-Small-3.2-24B-Instruct-2506128K—$0.08$0.2

API

GET/v1/models/deepinfra/mistralai/Mistral-Nemo-Instruct-2407