Ki api integration guide

Base URL and authentication

The API lives at https://api.kiapi.cc/v1. You get one active key per account, shown immediately after signup via Google or email. Change the base_url in your client and set the Authorization header to Bearer YOUR_KEY. This works with any standard OpenAI SDK.

• Base URL: https://api.kiapi.cc/v1
• Header: Authorization: Bearer YOUR_KEY

Copycurl https://api.kiapi.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fetch latest version from github repo"}]
  }'

Chat Completions endpoint

Send messages to POST /v1/chat/completions. Use the model ID uncensored for unrestricted outputs. The endpoint accepts standard chat formats with a context window of 100,000 tokens total. It returns text responses without content refusals for lawful adult use. No embeddings or image generation are available here.

Copyfrom openai import OpenAI

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

Streaming responses (SSE)

Enable streaming by setting stream: true. You receive server-sent events (SSE) for real-time token delivery. The final chunk contains the full usage statistics for billing. This is ideal for chat interfaces that need immediate partial responses. You can parse the SSE stream to update the UI instantly.

Copyimport OpenAI from "openai";

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

Function calling and JSON mode

Use response_format: {"type": "json_object"} for strict JSON outputs. The API supports tool definitions and tool choices for function calling. You can define custom tools in the tools array. The model will respond with structured data when required. This works alongside standard text generation.

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)

Model parameters and limits

Supports temperature, top_p, stop, seed, and penalty parameters. Max output is 16,000 tokens per request. You can send up to 300 requests per minute. Concurrency is limited to 8 simultaneous requests per key. The request body must stay under 8 MB. These limits ensure stable performance for uncensored generation tasks.

Token usage and billing

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. Credit is topped up via crypto only. Prepaid credit never expires. You pay only for real token usage. No monthly subscription fees apply. The system tracks usage accurately for billing.