Mistral: Ministral 3 3B 2512 - API in Egypt, billed in EGP
Liveministral-3b-2512The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Modality
Chat
Context window
131K tokens
Max output
105K tokens
Region
US
Published
29 Sept 2026
Pricing
Input
5.73
EGP per 1M tokens
Output
5.73
EGP per 1M tokens
Monthly cost example
372.46 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
Mistral: Ministral 3 3B 2512 works with any OpenAI-compatible SDK — point the base URL at https://dev-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://dev-backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="ministral-3b-2512",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://dev-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "ministral-3b-2512",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://dev-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ministral-3b-2512",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does Mistral: Ministral 3 3B 2512 cost?
5.73 EGP per 1M input tokens; 5.73 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: Ministral 3 3B 2512?
Mistral: Ministral 3 3B 2512 supports a context window of 131,072 tokens (131K), with up to 104,857 output tokens per response.
Where is Mistral: Ministral 3 3B 2512 hosted?
Mistral: Ministral 3 3B 2512 is served from US (US-hosted inference).
How do I use Mistral: Ministral 3 3B 2512 via the API?
Mistral: Ministral 3 3B 2512 is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://dev-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "ministral-3b-2512" and your API key.
Related models
View all models →Mistral Large
Mistral AI · Chat · 128K context
114.60 EGP / 1M input tokens
Mistral Large 2407
Mistral AI · Chat · 131K context
114.60 EGP / 1M input tokens
mistral-nemo-instruct-2407
Mistral AI · Chat · 131K context
1.09 EGP / 1M input tokens
mistral-small-24b-instruct-2501
Mistral AI · Chat · 33K context
2.87 EGP / 1M input tokens