modelgrep
M

Mistral: Mistral Nemo

mistralai/mistral-nemo

Cheaper than 99% of paidToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
77
98th fastest
Latency
273ms
first token
Input price
$0.020
4th cheapest
Context
131K

How it compares

Faster than67%
of all ranked models
Cheaper than99%
of all ranked models

Overview

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,...

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
DekaLLMfp8$0.020$0.03092.8%
DeepInfrafp8$0.020$0.04099.8%
Novitafp8$0.040$0.17074.2%
Mistral$0.150$0.15099.9%

Specifications

Context window131K
Max output
Knowledge cutoffApr 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Mistral Nemo FAQ

How much does Mistral Nemo cost?

Mistral Nemo costs $0.020 per million input tokens and $0.030 per million output tokens via OpenRouter, making it 4th cheapest of 298 paid models.

How fast is Mistral Nemo?

Mistral Nemo generates around 77 tokens per second with 273ms time-to-first-token (p50), the 98th fastest tracked model.

What is Mistral Nemo's context window?

Mistral Nemo supports a 131K-token context window. It accepts text input.

Compare head-to-head