How do I set a maximum amount of money the API could cost me?

The API does not support hard spending caps directly. Monitor usage via the response headers or track tokens in your application logic. Prepaid credit never expires, so you control the limit by your top-up amount.

What happens if I hit the rate limit?

You receive a 429 status code. The request consumes no tokens. Wait a few seconds and retry. You are limited to 300 requests per minute per key. Adjust your concurrency to stay under 8 simultaneous requests.

Is the uncensored model the same as Mistral AI's models?

No. We host an open-weight model tuned for no refusals. It is not GPT, Claude, or the official Mistral models. It is compatible with the same API structure but has its own model ID. Check the pricing page for details.

Hurtig start: Integrer Uncensored API

Base URL og autentificering

API'en lever ved https://api.mistralapipricing.com/v1. Send din nøgle i Authorization header. Mistral API-prissætningslogik gælder per token, så hold headers rene. Tilslutningsdygtighed verificeres med GET /v1/models.

Header: Authorization: Bearer YOUR_KEY
Base URL: https://api.mistralapipricing.com/v1

curl https://api.mistralapipricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the cost per token for each model."}]
  }'

Send din første anmodning

Kald chat/completions endpoint med dit model-ID. Den uncensored model svarer på standard prompts uden afvisninger. Input-tokens koster $0.15 per million. Output-tokens koster $0.50 per million. Fejl forbruger ingen kredit.

from openai import OpenAI

client = OpenAI(base_url="https://api.mistralapipricing.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node.js-integration

Brug det officielle SDK eller axios til at sende anmodninger. Indstil base URL'en korrekt. Model-ID'et er altid uncensored. Headers skal indeholde din bearer-token. Svar returnerer JSON-objekter. Håndter fejl elegant.

import OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming-svar

Aktivér streaming ved at indstille stream: true. Modtag tokens via Server-Sent Events. Den sidste chunk indeholder brugsdata. Dette reducerer den opfattede latens for lange outputs. Buffer tokens på klientsiden. Vis dem, mens de ankommer.

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function Calling og JSON-tilstand

Definer værktøjer i request body. Modellen returnerer gyldig JSON. Brug response_format: {"type": "json_object"} til streng output. Parser resultatet i din applikationslogik. Dette fungerer til automatiseringsopgaver. Valider skemaet på din side.

Begrænsninger, fejl og kontekst

Kontekstvinduet er på 100.000 tokens i alt. Anmodninger er begrænset til 300 i minuttet. Du får 8 samtidige anmodninger. En 401-fejl betyder en ugyldig nøgle. En 402-fejl indikerer utilstrækkelig kredit. En 429-fejl signalerer rate limiting. Det maksimale output er 16.000 tokens.

Hurtigstartsguide