Mistral Nemo

Provider: Mistral AI EU Official API price

Input price
$0.15
/ 1M tokens
Output price
$0.15
/ 1M tokens
Cache price
$0.015
/ 1M tokens (read)
Context
131K tokens
Max output 105K tokens

Overview

Mistral Nemo is a 12B budget model by Mistral AI featuring a 128k context window and built for multilingual text processing.

Strengths

  • Input and output priced at $0.15 per million tokens
  • Cached input discounted to $0.015 per million tokens
  • Large 131072 token context window capacity
  • Native function calling and JSON mode support

Best use cases

  • Multilingual translation and summarization pipelines
  • Structured data extraction tasks
  • Cost-sensitive batch processing workloads

Pricing position

Output pricing is $0.15/M, significantly cheaper than GPT-4o-mini at $0.60/M and Gemini 2.5 Flash at $1.25/M for the same input cost.

Caveats

Context window of 131072 tokens is smaller than newer alternatives like Mistral Small 4 with 262144 tokens.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
105K tokens
Knowledge cutoff
2024-04-30
Listed on OpenRouter
2024-07-19
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.02
1M (small app) 1 0.5 $0.22
10M (mid scale) 10 5 $2.25
100M (large) 100 50 $22.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API (mistralai/mistral-nemo)