Codestral

Outils

Mistral's specialized model for code generation. Optimized for coding tasks including code completion, generation, and explanation.

Identifiant du modèle — à coller dans votre code

mistralai/codestral

Tarifs · par million de tokens

Afficher les prix en

Entrée90 DA$0.36

Sortie270 DA$1.08

Entrée en cache90 DA$0.36

Fenêtre de contexte128KSortie max.: 32K

Capacités

Outils — Peut appeler vos fonctions / outils

Estimez votre coût

Tokens en entrée Tokens en sortie Requêtes

Coût estimé

Utiliser ce modèle

Créez un compte, rechargez en dinars et appelez-le avec votre clé :

from openai import OpenAI

client = OpenAI(
    base_url="https://dzrouter.com/v1",
    api_key="sk-dz-…",
)

reply = client.chat.completions.create(
    model="mistralai/codestral",
    messages=[{"role": "user", "content": "Salam!"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://dzrouter.com/v1",
  apiKey: process.env.DZROUTER_API_KEY,
});

const reply = await client.chat.completions.create({
  model: "mistralai/codestral",
  messages: [{ role: "user", content: "Salam!" }],
});
console.log(reply.choices[0].message.content);

curl https://dzrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $DZROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/codestral",
    "messages": [{"role": "user", "content": "Salam!"}],
    "stream": true
  }'

from anthropic import Anthropic

client = Anthropic(
    base_url="https://dzrouter.com",
    api_key="sk-dz-…",
)

msg = client.messages.create(
    model="mistralai/codestral",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Salam!"}],
)
print(msg.content[0].text)

Créer un compte gratuit

Autres modèles Mistral

mistralai/mistral-nemoMistral

mistralai/mistral-nemo

Entrée5,7 DA

Sortie9 DA

Contexte131K

mistralai/mistral-small-2603Mistral

mistralai/mistral-small-2603

Entrée45 DA

Sortie180 DA

Contexte350K

Mistral SmallMistral

mistralai/mistral-small-3.2-24b-instruct

Mistral's efficient 24B model optimized for simple tasks with low latency and 128K context. Great for classification, customer support, text generation, and multimodal tasks.

Entrée22,5 DA

Sortie60 DA

Contexte128K

mistralai/mistral-medium-3-5Mistral

mistralai/mistral-medium-3-5

Entrée450 DA

Sortie2 250 DA

Contexte128K

mistralai/mistral-large-2512Mistral

mistralai/mistral-large-2512

Entrée150 DA

Sortie450 DA