Back

Mistral: Mistral Nemo

Mistral
Input: text
Output: text
Released: Jul 19, 2024Updated: Mar 28, 2025

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.

It supports function calling and is released under the Apache 2.0 license.

131,072 Token Context

Process and analyze large documents and conversations.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra131K16K$0.01/M$0.03/M52.2 t/s234 ms
KlusterklusterAi131K131K$0.01/M$0.03/M93.7 t/s915 ms
Enferenfer131K131K$0.02/M$0.07/M39.9 t/s1147 ms
Parasailparasail131K131K$0.03/M$0.11/M147.3 t/s387 ms
NextBitnextBit128K-$0.03/M$0.07/M45.6 t/s1595 ms
InferenceNetinferenceNet16K16K$0.04/M$0.10/M64.7 t/s928 ms
NebiusnebiusAiStudio128K-$0.04/M$0.12/M44.4 t/s507 ms
NovitanovitaAi60K32K$0.04/M$0.17/M60.0 t/s1087 ms
InoCloudinoCloud131K131K$0.07/M$0.07/M101.4 t/s1297 ms
Mistralmistral131K-$0.15/M$0.15/M107.8 t/s253 ms
Azureazure128K-$0.30/M$0.30/M101.1 t/s1129 ms
Standard Pricing
Input Tokens
$0.00000001

per 1K tokens

Output Tokens
$0.000000028

per 1K tokens

Do Work. With AI.