mistral-nemo-instruct-2407

Live
Mistral AI

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Modality

Chat

Context window

131K tokens

Max output

16K tokens

Region

US

Published

Jul 21, 2026

Pricing

Input

1.07

EGP per 1M tokens

Output

1.69

EGP per 1M tokens

Use it via the API

mistral-nemo-instruct-2407 works with any OpenAI-compatible SDK — point the base URL at https://preprod-backend.sovereigneg.com/v1 and use your SovereignEG API key.

Run inference

OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://preprod-backend.sovereigneg.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="mistral-nemo-instruct-2407",
    messages=[
        {"role": "user", "content": "What are some fun things to do in Cairo?"}
    ],
)

print(response.choices[0].message.content)

Frequently asked questions

How much does mistral-nemo-instruct-2407 cost?

1.07 EGP per 1M input tokens; 1.69 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.

What is the context window of mistral-nemo-instruct-2407?

mistral-nemo-instruct-2407 supports a context window of 131,072 tokens (131K), with up to 16,384 output tokens per response.

Where is mistral-nemo-instruct-2407 hosted?

mistral-nemo-instruct-2407 is served from US (US-hosted inference).

How do I use mistral-nemo-instruct-2407 via the API?

mistral-nemo-instruct-2407 is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://preprod-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "mistral-nemo-instruct-2407" and your API key.