Set up Codex & OpenAI clients

TokAPI implements the OpenAI Responses and Chat Completions APIs, so OpenAI Codex and any OpenAI-compatible SDK or tool work by changing two values: the base URL and the API key.

Base URL and key

Setting	Value
Base URL	`https://api.tokapi.ai`
API key	`sk-lazytech-...`
Auth header	`Authorization: Bearer sk-lazytech-...`

Environment variables

Most OpenAI-compatible clients read these:

export OPENAI_BASE_URL="https://api.tokapi.ai/v1"
export OPENAI_API_KEY="sk-lazytech-..."

Endpoints

Use the OpenAI-compatible endpoints:

POST /v1/responses — the Responses API (recommended).
POST /v1/chat/completions — the Chat Completions API.

Use OpenAI model IDs such as gpt-5.5 or gpt-5.4.

Example — Responses API

curl https://api.tokapi.ai/v1/responses \
  -H "Authorization: Bearer sk-lazytech-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "Write a haiku about fast tokens."
  }'

Example — Chat Completions API

curl https://api.tokapi.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-lazytech-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Set "stream": true to receive Server-Sent Events. See the API Reference for the full endpoint list.