Mistral Nemo Instruct (2407)

by Mistral · Released , 220 days after Mistral Embed · Announcement · All Mistral releases

Mistral Nemo Instruct is an instruction-tuned 12 billion parameter model released July 2024, jointly trained by Mistral AI and NVIDIA. It achieves benchmark scores of 83.5% on HellaSwag, 76.8% on Winogrande, and 68% on MMLU (5-shot), with strong multilingual performance across languages including French, German, Spanish, Italian, Portuguese, Russian, Chinese, and Japanese. Built as a drop-in replacement for Mistral 7B systems, the model supports function calling and was trained with a substantial proportion of multilingual and code data. It uses Tekken tokenization for efficient code handling and is quantization-aware, enabling FP8 inference without performance loss.

Sign up without a credit card · OpenAI SDK compatible
Input
$0.02 / 1M
Output
$0.03 / 1M
Cache read
$0.0034 / 1M
Context
131K tokens
Max output
131K tokens
Routes
2 EU · US

Available routes

Mistral Nemo Instruct (2407) runs on 2 different routes through the Opper gateway.

ProviderRegionZero data retentionTrainingInputOutputCache read
USNo$0.02$0.03Input price
EUNo$0.02$0.03$0.0034Not offered on this route

Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by FlexAI. See every Mistral model hosted in the EU. One route also sells flex processing: the same model at another price, picked per request with service_tier. How service tiers work.

Live routes and prices as JSON: api.opper.ai/v3/models?q=mistral-nemo-instruct-2407

Key info

Input
Output
Features
Context window
131K
Max output
131K
Input price
$0.02 /1M
Output price
$0.03 /1M
Released
Web search
  • EU residency available on FlexAI
  • US residency available on DeepInfra
  • Zero data retention on pay-as-you-go
  • No training by default

Uptime and availability

One of Mistral Nemo Instruct (2407)'s 2 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

99.75%route uptime, last 30 days
Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route is not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Mistral Nemo Instruct (2407) has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
No classifier
Transfer mechanism
SCCs

FlexAI — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
No classifier
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
Transfer mechanism
Not applicable — data stays in EU

Get started

Call Mistral Nemo Instruct (2407) through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Mistral Nemo Instruct (2407) is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "mistral-nemo-instruct-2407",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Use Mistral Nemo Instruct (2407) in your apps

Pick your tool, then choose Mistral Nemo Instruct (2407) to see how to run it through Opper.

Use Mistral Nemo Instruct (2407) with tools

The tools Mistral Nemo Instruct (2407) can use through Opper. Pick one to see how to set it up.

Compare Mistral Nemo Instruct (2407) with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Mistral

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation