SDKs
Use the OpenAI SDKs (or any compatible client) against TokenMoo.
TokenMoo is OpenAI-compatible, so existing SDKs work after changing the base URL and key.
Python
from openai import OpenAI
client = OpenAI(
api_key="sk-xxx",
base_url="https://www.tokenmoo.com/v1",
)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Streaming:
stream = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Count to five"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")JavaScript / TypeScript
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'sk-xxx',
baseURL: 'https://www.tokenmoo.com/v1',
});
const response = await client.chat.completions.create({
model: 'gpt-4o-mini',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);Other tools
Any client that lets you set a base URL works, including LangChain, LlamaIndex, the Vercel AI SDK and most chat front-ends. When asked for:
- API base / base URL:
https://www.tokenmoo.com/v1 - API key: your
sk-...key - Model name: any model from the Model Square page
If a tool only accepts an OpenAI-style endpoint without a custom base URL, point its proxy setting at https://www.tokenmoo.com and keep the /v1 path.