Quickstart

cheapapi (a cheapapi product) is a drop-in base URL. Point an OpenAI, Anthropic or Gemini client at it and use one key.

1. Create an account. The dashboard is ready as soon as you sign up.
2. Open API keys, click Create, and copy the key. Keep it on the server. Rotate it if it leaks.
3. Set the base URL for your client. OpenAI-format tools need /v1. Anthropic and Gemini clients must not have it.
4. Send a test request. Then add credit in Wallet when you are ready to run real traffic.

First request

curl /v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Reply with pong"}]
  }'

Base URLs

Next

Model IDs

Use model IDs exactly as they appear in the catalogue. A misspelled ID returns 503 model_not_found.

Live availability and pack rates sit on the model list. The calculator converts list prices into what a pack actually pays.

Keys and limits

Create keys in the dashboard. Use one key per project so logs stay readable and a leak only hits that project.

• Spending cap. The key stops when it reaches its cap, even if the wallet still has credit.
• Expiry. Useful for demos, contractors and CI.
• Model allow-list. Limit a key to the models you choose.
• IP allow-list. Restrict a production key to your servers.

OpenAI SDK

Any OpenAI-compatible client works the same way: base URL plus /v1, Bearer key, catalogue model ID.

Python

from openai import OpenAI
client = OpenAI(base_url="/v1", api_key="sk-your-key")

stream = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Write a haiku about latency"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Node

import OpenAI from "openai";
const client = new OpenAI({
  apiKey: process.env.TOKENMASTER_API_KEY,
  baseURL: "/v1",
});
const completion = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

n8n, LangChain, LlamaIndex, OpenClaw, Hermes Agent and similar tools follow this path. Point them at the OpenAI-compatible provider and the same base URL.

Anthropic SDK

Do not add /v1 to an Anthropic base URL. The SDK appends /v1/messages itself.

import anthropic
client = anthropic.Anthropic(base_url="", api_key="sk-your-key")
msg = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)

Gemini (CLI and SDK)

Gemini models only work here once they are listed as live in the catalogue.

export GOOGLE_GEMINI_BASE_URL=
export GEMINI_API_KEY=sk-your-key
gemini

With @google/genai, pass httpOptions: { baseUrl: "" }.

Claude Code

Anthropic base URL, no /v1. Auth token is your cheapapi key.

Environment

export ANTHROPIC_BASE_URL=
export ANTHROPIC_AUTH_TOKEN=sk-your-key
export ANTHROPIC_MODEL=claude-sonnet-4-6
export ANTHROPIC_SMALL_FAST_MODEL=claude-haiku-4-5
claude

To make this permanent, add the same variables under "env" in ~/.claude/settings.json.

Cursor

In Settings → Models, paste your key under OpenAI API Key. Turn on Override OpenAI Base URL and set it to . Add model IDs such as claude-sonnet-4-6 or gpt-5.6-terra under Add model.

Cline / Roo Code

Pick the OpenAI Compatible provider. Set the base URL to , add your key, and type the model ID. For Claude models you can also use the Anthropic provider with a custom base URL of .

Codex CLI

# ~/.codex/config.toml
model = "gpt-5.6-sol"
model_provider = "tokenmaster"

[model_providers.tokenmaster]
name = "cheapapi"
base_url = "/v1"
env_key = "TOKENMASTER_API_KEY"

Run export TOKENMASTER_API_KEY=sk-your-key, then start codex.

Balance and usage

curl /api/usage/token/ -H "Authorization: Bearer sk-your-key"

The response contains total_available and total_used in quota units, where 500,000 units equal $1. The balance checker does the conversion for you. For per-request detail (model, tokens, cost, latency), open Usage logs.

Errors

Support

Signed-in users can find support channels in the dashboard. For a large-volume package or a dedicated channel pool, contact us through the contact page and include expected monthly token volume.