Documentación

Inicio rápido

TokenGate es 100% compatible con la API de OpenAI. Solo cambiás el base_url y la API key.

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokengate.io/v1",
    api_key="tg_live_..."  # desde /dashboard/keys
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hola"}]
)
print(response.choices[0].message.content)

Con curl

curl https://api.tokengate.io/v1/chat/completions \
  -H "Authorization: Bearer tg_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hola"}],
    "stream": false
  }'

Streaming SSE

Agregá "stream": true para recibir la respuesta token por token.

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Contame un chiste"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Listar modelos disponibles

GET /v1/models
Authorization: Bearer tg_live_...

# Response: lista de modelos en formato OpenAI

Respuestas de error