API documentation

WorldAPI is OpenAI-compatible: use any OpenAI SDK with a different base URL and your WorldAPI key.

Base URLhttps://worldapi.cc/v1

Quickstart

Create an API key in the dashboard, export it as WORLDAPI_KEY, then send a chat completion. Create a key

curl

curl https://worldapi.cc/v1/chat/completions \
  -H "Authorization: Bearer $WORLDAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write a haiku about the sea."}
    ],
    "stream": true
  }'

Python · openai ≥ 1.0

from openai import OpenAI

client = OpenAI(
    base_url="https://worldapi.cc/v1",
    api_key="wapi-sk-...",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Summarize this in one line: ..."}],
)
print(resp.choices[0].message.content)
print(resp.usage)  # prompt_tokens, completion_tokens, total_tokens

TypeScript · openai

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://worldapi.cc/v1",
  apiKey: process.env.WORLDAPI_KEY,
});

const stream = await client.chat.completions.create({
  model: "gemini-3.5-flash-lite",
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Authentication

Send your key as a Bearer token in the Authorization header (x-api-key is also accepted). Keys start with wapi-sk- and are shown only once at creation; revoke and recreate them from the dashboard.

Authorization: Bearer wapi-sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

Models

Use the public id from the rate card as the model parameter. GET /v1/models returns the same list with prices. See the full rate card

GET https://worldapi.cc/v1/models

gemini-3.1-progemini-3.8-flashgemini-3.5-flashgemini-3.5-flash-litegemini-3.1-flash-litellama-4-maverickqwen3-235bglm-4.7kimi-k2-thinkingclaude-opus-5claude-sonnet-5claude-opus-4.8claude-sonnet-4.6claude-haiku-4.5gemma-4-26bgpt-oss-120bgpt-oss-20bglm-5kimi-k2.5nova-premiernova-pronova-2-litenova-lite

Billing & usage

Accounts are prepaid. Each request is priced per token and deducted from your balance; a request that starts with zero balance is refused with 402.

Each model has its own discounted price next to the vendor's official price; see the rate card.

Responses carry the standard OpenAI usage object (streaming: in the final chunk). Per-request cost is shown in the dashboard.

usage

"usage": {
  "prompt_tokens": 120,
  "completion_tokens": 48,
  "total_tokens": 168
}

Errors

Errors use the OpenAI envelope: { error: { message, type, code } }. Failed requests are not charged.

HTTP	code	Meaning
401	`invalid_api_key`	Missing, malformed or revoked API key.
402	`insufficient_balance`	Balance is zero. Buy a usage pack in the dashboard.
404	`model_not_found`	Unknown model id.
429	`rate_limit_error`	The upstream provider rate-limited the request. Retry with backoff.
502 / 504	`upstream_error`	The upstream provider failed or timed out. Not charged; retry.

402

{
  "error": {
    "message": "Your WorldAPI balance is exhausted. Buy a usage pack at https://worldapi.cc/dashboard/billing.",
    "type": "insufficient_quota",
    "code": "insufficient_balance"
  }
}

Limits

Request bodies up to 6 MB; streaming responses up to 5 minutes.
Up to 20 active API keys per account.
Per-account rate limits follow the cloud quotas we hold; contact support for reserved throughput.