Is the Venice LLM API compatible with OpenAI SDKs?

Yes. The API uses the same request and response structures as the OpenAI chat completions endpoint. You can use the official OpenAI Python, Node.js, or Go SDKs by simply changing the base_url and providing your Venice API key.

How does prepaid billing work without a subscription?

You pay only for the tokens you use, with no monthly fees. Credits are topped up exclusively via crypto (USDT on TRC20 or USDC on Base). Errors and refusals are free, and your credit never expires.

What is the context window limit for requests?

The model supports a 100,000-token context window, counting both input and output tokens. You can generate up to 16,000 tokens in a single response, or adjust this limit using the max_tokens parameter.

เอกสาร API - OpenAI Compatible Endpoints

Authentication and base URLs

The Venice API authenticates via a bearer token passed in the Authorization header. All requests route through the standard OpenAI base URL structure to ensure compatibility.

Base URL: https://api.llmvenice.com/v1

Header: Authorization: Bearer YOUR_API_KEY

Keep your key secure. You can regenerate it at any time, though a new key replaces the old one immediately.

Chat completions endpoint

Send text prompts to the uncensored model using the POST /v1/chat/completions endpoint. The system processes text input and returns text output, supporting a 100,000-token context window for long-form analysis.

Requests are billed by real token usage. Errors and refusals incur no charge. The model ID for this uncensored instance is uncensored.

Streaming responses

Enable real-time token delivery by setting stream: true. The API returns Server-Sent Events (SSE), allowing your application to render text as it generates. Token usage statistics appear in the final chunk of the stream.

JSON mode and function calling

Structure your output strictly by adding "response_format": {"type": "json_object"} to your payload. The API also supports standard tool definitions for function calling, enabling dynamic data retrieval and structured logic integration.

Rate limits and quotas

Each API key supports 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. Output is capped at 16,000 tokens per request unless you specify a lower limit via the max_tokens parameter.

Error handling

Handle standard HTTP error codes to manage client-side failures. A 401 error indicates an invalid or expired API key. A 402 error means your prepaid credit is exhausted; top up via crypto to resume service. A 429 error signals that you have exceeded the 300 requests per minute limit. Wait briefly before retrying.

cURL

curl https://api.llmvenice.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the main dependencies for the latest release"}]
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.llmvenice.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

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmvenice.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

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)

API Reference