---
last_updated: 2026-11-20
source_url: https://opper.ai/mistral/mistral-nemo-instruct-2407
title: "Mistral Nemo Instruct (2407) by Mistral"
description: "Mistral Nemo Instruct, instruction-tuned 12B model with 128k context, multilingual strengths, and efficient quantized inference."
---

# Mistral Nemo Instruct (2407)

By [Mistral](https://opper.ai/mistral).

Released 18 Jul 2024, 220 days after [Mistral Embed](https://opper.ai/mistral/mistral-embed) · [Announcement](https://docs.mistral.ai/models/mistral-nemo-12b-24-07) · [All Mistral releases](https://opper.ai/model-releases/mistral)

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.

## Available routes

Mistral Nemo Instruct (2407) runs on 2 different routes through the Opper gateway. Prices are per 1M tokens. In the EU it is served by FlexAI. [See every Mistral model hosted in the EU](https://opper.ai/models/eu/mistral). One route also sells flex processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=mistral-nemo-instruct-2407.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepInfra](https://opper.ai/provider/deepinfra) | `deepinfra/mistralai/Mistral-Nemo-Instruct-2407` | US (United States) | Yes | No | $0.02 | $0.03 | Input price |
| [DeepInfra](https://opper.ai/provider/deepinfra), Flex | `deepinfra:flex/mistralai/Mistral-Nemo-Instruct-2407` | US (United States) | Yes | No | $0.02 | $0.02 | $0.02 |
| [FlexAI](https://opper.ai/provider/flexai) | `flexai:eu/Mistral-Nemo-Instruct-2407-FP8` | EU | Yes | No | $0.02 | $0.03 | $0.0034 |

## Key info

- Model id: `mistral-nemo-instruct-2407` (routes across DeepInfra, FlexAI)
- Input: Text
- Output: Text
- Features: Tools
- Context window: 131K
- Max output: 131K
- Input price: $0.02 per 1M tokens
- Output price: $0.03 per 1M tokens
- Released: 18 Jul 2024
- EU residency available on FlexAI
- US residency available on DeepInfra
- Zero data retention on pay-as-you-go
- No training by default

## 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

Verified by Opper on 2026-10-19.

### 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

Verified by Opper on 2026-11-10.

## 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

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Mistral Nemo Instruct (2407)
```

### Or call it directly

OpenAI:

```javascript
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);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "mistral-nemo-instruct-2407",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "mistral-nemo-instruct-2407",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-nemo-instruct-2407",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Mistral Nemo Instruct (2407) in your apps

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

- [Claude Code](https://opper.ai/apps/claude-code/mistral-nemo-instruct-2407)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/mistral-nemo-instruct-2407)
- [Codex](https://opper.ai/apps/codex/mistral-nemo-instruct-2407)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/mistral-nemo-instruct-2407)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/mistral-nemo-instruct-2407)
- [Aider](https://opper.ai/apps/aider/mistral-nemo-instruct-2407)
- [Goose](https://opper.ai/apps/goose/mistral-nemo-instruct-2407)
- [Droid](https://opper.ai/apps/droid/mistral-nemo-instruct-2407)
- [OpenCode](https://opper.ai/apps/opencode/mistral-nemo-instruct-2407)
- [Pi](https://opper.ai/apps/pi/mistral-nemo-instruct-2407)
- [OpenClaw](https://opper.ai/apps/openclaw/mistral-nemo-instruct-2407)
- [Hermes](https://opper.ai/apps/hermes/mistral-nemo-instruct-2407)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/mistral-nemo-instruct-2407)
- [OmniRoute](https://opper.ai/apps/omniroute/mistral-nemo-instruct-2407)
- [Cursor](https://opper.ai/apps/cursor/mistral-nemo-instruct-2407)
- [Cline](https://opper.ai/apps/cline/mistral-nemo-instruct-2407)
- [Continue](https://opper.ai/apps/continue/mistral-nemo-instruct-2407)
- [Kilo Code](https://opper.ai/apps/kilo-code/mistral-nemo-instruct-2407)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/mistral-nemo-instruct-2407)
- [Zed](https://opper.ai/apps/zed/mistral-nemo-instruct-2407)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/mistral-nemo-instruct-2407)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/mistral-nemo-instruct-2407)
- [n8n](https://opper.ai/apps/n8n/mistral-nemo-instruct-2407)
- [LibreChat](https://opper.ai/apps/librechat/mistral-nemo-instruct-2407)
- [Open WebUI](https://opper.ai/apps/open-webui/mistral-nemo-instruct-2407)
- [See all apps](https://opper.ai/apps)

## Other models from Mistral

- [Mistral Large 4](https://opper.ai/mistral/mistral-large-4)
- [Mistral Medium 3.5](https://opper.ai/mistral/mistral-medium-3-5)
- [Mistral Small 4](https://opper.ai/mistral/mistral-small-2603)
- [Mistral Large 3](https://opper.ai/mistral/mistral-large-3)
- [Voxtral TTS 3](https://opper.ai/mistral/voxtral-mini-tts-3-0)
- [Timestral 5M](https://opper.ai/mistral/timestral-5m)
