TTokenPortal

Quickstart

TokenPortal is OpenAI-compatible — change the base URL to access 150+ models instantly. Claude Code / Anthropic-native, Gemini, and the OpenAI Responses API are also supported, see below.

1
Sign up & log in
Create an account by email and get free credits.
2
Create an API key
Generate an sk- key on the API Keys page in your workspace.
3
Swap the base URL
Point your SDK's baseURL to https://staging-dp.taotoken.io/v1 and call with your key.
API Base URL (OpenAI-compatible)
https://staging-dp.taotoken.io/v1
API Base URL (Claude Code / Anthropic-native)
https://staging-dp.taotoken.io

No /v1 — Claude Code / the Anthropic SDK append /v1/messages themselves.

Make your first call

OpenAI-compatible

Python (openai SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://staging-dp.taotoken.io/v1",
    api_key="sk-your-tokenportal-key",
)

resp = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
Node.js (openai SDK)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://staging-dp.taotoken.io/v1",
  apiKey: process.env.TOKENPORTAL_API_KEY,
});

const res = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(res.choices[0].message.content);
cURL
curl https://staging-dp.taotoken.io/v1/chat/completions \
  -H "Authorization: Bearer sk-your-tokenportal-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Code / Anthropic-native

Environment variables
ANTHROPIC_BASE_URL=https://staging-dp.taotoken.io
ANTHROPIC_API_KEY=sk-your-tokenportal-key
ANTHROPIC_MODEL=anthropic/claude-opus-4.8
cURL
curl https://staging-dp.taotoken.io/v1/messages \
  -H "x-api-key: sk-your-tokenportal-key" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.8",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gemini-compatible

Native Gemini request/response shape at /v1/models/{model}:generateContent — model id keeps the provider prefix.

cURL
curl https://staging-dp.taotoken.io/v1/models/google/gemini-3.1-pro-preview:generateContent \
  -H "Authorization: Bearer sk-your-tokenportal-key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "Hello!"}]}]
  }'

OpenAI Responses API

Python (openai SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://staging-dp.taotoken.io/v1",
    api_key="sk-your-tokenportal-key",
)

resp = client.responses.create(
    model="openai/gpt-4o",
    input="Hello!",
)
print(resp.output_text)
cURL
curl https://staging-dp.taotoken.io/v1/responses \
  -H "Authorization: Bearer sk-your-tokenportal-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "input": "Hello!"
  }'