> ## Documentation Index
> Fetch the complete documentation index at: https://docs.teamsoclo.site/llms.txt
> Use this file to discover all available pages before exploring further.

# cURL / Python / Node.js

> Llama a la API directamente con las bibliotecas oficiales de OpenAI

Cualquier biblioteca oficial de OpenAI funciona; solo cambia `base_url`. Los ejemplos usan `gpt-5.6-sol`; para el paquete Astra usa `gpt-astra`.

## Chat Completions

<CodeGroup>
  ```bash cURL theme={null}
  curl https://gpt.teamsoclo.site/v1/chat/completions \
    -H "Authorization: Bearer sk-xxx" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-5.6-sol",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain closures in JavaScript"}
      ]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-xxx",
      base_url="https://gpt.teamsoclo.site/v1",
  )

  resp = client.chat.completions.create(
      model="gpt-5.6-sol",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Explain closures in JavaScript"},
      ],
  )

  print(resp.choices[0].message.content)
  print(resp.usage)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai"

  const client = new OpenAI({
    apiKey: "sk-xxx",
    baseURL: "https://gpt.teamsoclo.site/v1",
  })

  const resp = await client.chat.completions.create({
    model: "gpt-5.6-sol",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Explain closures in JavaScript" },
    ],
  })

  console.log(resp.choices[0].message.content)
  console.log(resp.usage)
  ```
</CodeGroup>

<Warning>
  `base_url` debe incluir `/v1` y **no** debe terminar con `/`. La biblioteca añade `/chat/completions` por sí misma.
</Warning>

Las respuestas siguen exactamente el esquema de OpenAI: `id` es `chatcmpl-...`, `usage` tiene `prompt_tokens`, `completion_tokens` y `completion_tokens_details.reasoning_tokens`. El cupo se cobra exactamente `usage.total_tokens`.

## Responses API

Codex y los SDK más nuevos usan este protocolo. La configuración de razonamiento está en `reasoning.effort`.

<CodeGroup>
  ```bash cURL theme={null}
  curl https://gpt.teamsoclo.site/v1/responses \
    -H "Authorization: Bearer sk-xxx" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-5.6-sol",
      "input": "Write a Python function that checks for primes",
      "reasoning": {"effort": "medium"}
    }'
  ```

  ```python Python theme={null}
  resp = client.responses.create(
      model="gpt-5.6-sol",
      input="Write a Python function that checks for primes",
      reasoning={"effort": "medium"},
  )
  print(resp.output_text)
  ```
</CodeGroup>

## Esfuerzo de razonamiento

Con Chat Completions usa `reasoning_effort` (`low`, `medium`, `high`). Sin configurar, el gateway usa `high`. Para tareas simples establece `low` para ahorrar tokens:

```python theme={null}
resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    reasoning_effort="low",
    messages=[{"role": "user", "content": "Translate to French: good morning"}],
)
```

<Warning>
  `reasoning_effort` es solo para Chat Completions. Con la Responses API usa `reasoning: {"effort": ...}`; enviar `reasoning_effort` a `/v1/responses` se rechaza con "Unsupported parameter".
</Warning>

## Streaming

<CodeGroup>
  ```python Python theme={null}
  stream = client.chat.completions.create(
      model="gpt-5.6-sol",
      messages=[{"role": "user", "content": "Write a short paragraph about autumn"}],
      stream=True,
      stream_options={"include_usage": True},
  )

  for chunk in stream:
      if chunk.choices and chunk.choices[0].delta.content:
          print(chunk.choices[0].delta.content, end="", flush=True)
      if chunk.usage:
          print("\n", chunk.usage)
  ```

  ```bash cURL theme={null}
  curl https://gpt.teamsoclo.site/v1/chat/completions \
    -H "Authorization: Bearer sk-xxx" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-5.6-sol",
      "messages": [{"role": "user", "content": "Write a short paragraph about autumn"}],
      "stream": true,
      "stream_options": {"include_usage": true}
    }'
  ```
</CodeGroup>

<Tip>
  En preguntas difíciles el modelo puede pensar un rato antes del primer token. Usa `stream: true` para que la conexión no se corte. `stream_options.include_usage` hace que el último fragmento lleve `usage` para que puedas conciliar el cupo tú mismo.
</Tip>

## Enviar imágenes (visión)

Las imágenes van en el array `content`, como URL pública o base64 para archivos locales.

<CodeGroup>
  ```python Image URL theme={null}
  resp = client.chat.completions.create(
      model="gpt-5.6-sol",
      messages=[{
          "role": "user",
          "content": [
              {"type": "text", "text": "What error does this show?"},
              {"type": "image_url", "image_url": {"url": "https://example.com/screenshot.png"}},
          ],
      }],
  )
  print(resp.choices[0].message.content)
  ```

  ```python Local file (base64) theme={null}
  import base64

  with open("screenshot.png", "rb") as f:
      b64 = base64.b64encode(f.read()).decode()

  resp = client.chat.completions.create(
      model="gpt-5.6-sol",
      messages=[{
          "role": "user",
          "content": [
              {"type": "text", "text": "What error does this show?"},
              {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
          ],
      }],
  )
  print(resp.choices[0].message.content)
  ```
</CodeGroup>

<Warning>
  Las imágenes cuestán tokens según su tamaño. Recorta la parte relevante en lugar de enviar una captura de pantalla 4K completa.
</Warning>

## Modelos y cupo mediante API

```bash theme={null}
# Modelos que puede llamar esta clave
curl https://gpt.teamsoclo.site/v1/models -H "Authorization: Bearer sk-xxx"

# Cupo (endpoints OpenAI heredados)
curl https://gpt.teamsoclo.site/v1/dashboard/billing/subscription -H "Authorization: Bearer sk-xxx"
curl https://gpt.teamsoclo.site/v1/dashboard/billing/usage -H "Authorization: Bearer sk-xxx"
```

`subscription` devuelve el total en `hard_limit_usd`; `usage` devuelve lo usado en `total_usage`, en **centavos** (divide entre 100 antes de comparar). La [página de verificación](https://gpt.teamsoclo.site/check) hace esto por ti.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.