Claude prezzi: openai compatible api docs

Quickstart: Connect with the Official OpenAI SDK

Start by installing the official SDK for your language. Set the base URL to https://api.claudeprezzi.com/v1 and provide your API key. This configuration routes requests to our dedicated uncensored model.

• Install: pip install openai or npm install openai
• Configure: Point to our base URL.

Copycurl https://api.claudeprezzi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "explain the dependency injection pattern"}]
  }'

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.claudeprezzi.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)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudeprezzi.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);

Endpoints: /v1/chat/completions and /v1/models

We offer exactly two endpoints for text generation and model discovery. Use POST /v1/chat/completions to generate text and GET /v1/models to verify availability.

Copycurl https://api.claudeprezzi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "explain the dependency injection pattern"}]
  }'

There are no embeddings, audio, or image endpoints. This simplicity ensures consistent routing to our single uncensored model.

Parameters: Temperature, Top P, and Stop Sequences

Control output randomness with standard parameters. Set temperature for creativity and top_p for nucleus sampling.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.claudeprezzi.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)

Use stop to halt generation at specific sequences. Our model respects these constraints precisely, allowing for clean structural outputs.

Advanced: Function Calling, JSON Mode, and Streaming

Enable structured outputs with response_format: {"type": "json_object"}. Use tools for function calling and enable streaming via SSE.

Copystream = 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)

Streaming provides real-time token usage in the final chunk. This approach reduces latency perception for long responses.

Limits: 300 RPM, 8 Concurrent Requests, 8MB Body

Each API key supports 300 requests per minute. You can run 8 concurrent requests simultaneously. The request body must not exceed 8 MB.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudeprezzi.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);

Exceeding these limits returns a 429 error. Plan your concurrency accordingly to avoid throttling during high-volume tasks.

Usage: Token Counting and Billing Details

Billing is strictly based on token usage. Input tokens cost $0.15 per 1M tokens. Output tokens cost $0.50 per 1M tokens.

Copycurl https://api.claudeprezzi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "explain the dependency injection pattern"}]
  }'

Errors and refusals consume no tokens. Your prepaid credit never expires, and you only pay for what you actually use.