Ilustración de escena, no generada por este modelo
Modelo:
Precio: 1.2 credits per 1K input tokens · ≈ $0.0006 · 2.4 credits per 1K output tokens · ≈ $0.0012Alta estabilidad, con registros de uso detallados en la plataforma APIAny.
Preajuste sin resultado generado
Sampling temperature.
Maximum output tokens.
Optional reasoning effort. Leave unset to use the model default. Higher effort can use more tokens and time.
Web search
Search the web before answering when current information is needed.
Estimación en USD ≈ $0.005: Nivel $999: 1 USD = 2,000 créditos.
Historial
Guardado localmente en este navegador
0 en curso · 0 completadas
Entrada
≈ $0.0006
Salida
≈ $0.0012
Lectura de caché
≈ $0.0006
Contexto
Salida máx.
Autenticación
Cada solicitud debe incluir un token Bearer en el encabezado Authorization. Crea tu API Key en la consola.
Authorization: Bearer YOUR_API_KEYhttps://apiany.ai/v1/chat/completionsParámetros de solicitud
| Parámetro | Tipo | Obligatorio | Notas |
|---|---|---|---|
model | cadena | Obligatorio | Identificador del modelo a llamar; usa el ID de este modelo. |
messages | array | Obligatorio | Historial de mensajes en formato de chat OpenAI (role + content). |
stream | booleano | Opcional | Si es true, la respuesta se devolverá como stream SSE. |
Ejemplo de solicitud
curl "https://apiany.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.6",
"messages": [
{
"role": "user",
"content": "Write a short decision memo using these fictional constraints: a two-person studio needs shared file review in 10 days; first-year budget 600 USD. Option A costs 20 USD/month and is ready now but lacks custom branding. Option B takes 15 engineering days plus 100 USD/year hosting and supports branding. Branding is desirable, not required; neither option has verified backup recovery. Recommend an option, show budget arithmetic and state the verification still needed."
}
],
"temperature": 0.7,
"max_tokens": 4096,
"reasoning_effort": "high",
"web_search": false
}'Ejemplo de respuesta
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "grok-4.6",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 18,
"total_tokens": 30
}
}
