TextoGeminiGemini.2.5.FlashOpenai.Sdk

Gemini 2.5 Flash - OpenAI SDK - Inicio rápido

Llamar al modelo gemini-2.5-flash usando el formato del SDK de OpenAI

Modo de procesamiento síncrono, devuelve el contenido de la conversación en tiempo real
Conversación de texto plano: Diálogo de un solo turno o múltiples turnos con contexto, ver ejemplos simple_text y multi_turn en las muestras de código
Prompt del sistema: Personalizar el rol y comportamiento de la IA, ver ejemplo system_prompt en las muestras de código
Entrada multimodal: Soporta entrada mixta de texto + imagen, ver ejemplos vision y multi_image en las muestras de código

<Note> **BaseURL**: La BaseURL predeterminada es `https://api.starmagic.ai`, que ofrece mejor compatibilidad con modelos de texto y admite conexiones persistentes. `https://api.starmagic.ai` es el endpoint principal para servicios multimodales y actúa como dirección de respaldo para los modelos de texto. </Note>

Autorización

AuthorizationstringheaderObligatorio

##Todas las APIs requieren autenticación Bearer Token## **Obtener API Key:** Visita la [Página de gestión de API Key](https://starmagic.ai/app/api-keys) para obtener tu API Key **Agregar al encabezado de la solicitud:** ``` Authorization: Bearer YOUR_API_KEY ```

Authorization: Bearer YOUR_API_KEY

Cuerpo de solicitud

application/json

modelenum<gemini-2.5-flash>Obligatorio

Nombre del modelo de chat

"gemini-2.5-flash"

messagesobject[]Obligatorio

Lista de mensajes de chat, soporta diálogo de múltiples turnos y entrada multimodal

[
  {
    "role": "user",
    "content": null,
    "tool_call_id": "string"
  }
]

streamboolean

Si se devuelve la respuesta en modo streaming - `true`: Retorno en streaming, recibe contenido en fragmentos en tiempo real - `false`: Devuelve la respuesta completa de una sola vez

false

max_completion_tokensinteger

Maximum number of completion tokens for the generated response, corresponding to Gemini's maxOutputTokens.

max_tokensinteger

Maximum number of tokens for the generated response, compatible with the legacy OpenAI parameter.

temperaturenumber

Temperatura de muestreo, controla la aleatoriedad de la salida **Descripción**: - Valores más bajos (ej., 0.2): Salida más determinista y enfocada - Valores más altos (ej., 1.5): Salida más aleatoria y creativa

0.7

top_pnumber

Parámetro de Nucleus Sampling **Descripción**: - Controla el muestreo de tokens con probabilidad acumulada - Por ejemplo, 0.9 significa seleccionar entre tokens con probabilidad acumulada de hasta el 90% - Valor predeterminado: 1.0 (considera todos los tokens) **Recomendación**: No ajustar temperature y top_p simultáneamente

0.9

frequency_penaltynumber

Frequency penalty coefficient. Range: -2.0 to 2.0. Corresponds to Gemini's frequencyPenalty.

presence_penaltynumber

Presence penalty coefficient. Range: -2.0 to 2.0. Corresponds to Gemini's presencePenalty.

stopobject

Stop sequences. Supports a string or string array, corresponding to Gemini's stopSequences.

ninteger

Number of generated candidates.

reasoning_effortenum<none | low | medium | high>

Limita el esfuerzo de razonamiento. Gemini 2.5 Flash y Flash Lite admiten none para desactivar el razonamiento; low/medium/high corresponden a distintos presupuestos.

"medium"

seedinteger

Random seed used to make output as reproducible as possible, corresponding to Gemini's seed.

logprobsboolean

Whether to return token logprob information, corresponding to Gemini's responseLogprobs.

true

top_logprobsinteger

Number of top logprob values returned for each token, corresponding to Gemini's logprobs.

response_formatobject

Response format settings, supporting JSON mode and JSON Schema, corresponding to Gemini's responseMimeType, responseSchema and responseJsonSchema.

stream_optionsobject

Streaming response options. Can be set when stream is true.

{
  "include_usage": true
}

toolsobject[]

List of tool definitions for Function Calling.

[
  {
    "type": "function",
    "function": {
      "name": "string",
      "description": "string",
      "parameters": {}
    }
  }
]

tool_choiceobject

Controls tool-calling behavior.

extra_bodyobject

Gemini extension parameters.

{
  "google": {
    "cached_content": "string",
    "thinking_config": {}
  }
}

Respuesta

application/json

成功

Cuerpo de respuesta

idstring

Identificador único para la completación de chat

"chatcmpl-20251010015944503180122WJNB8Eid"

modelstring

Nombre del modelo realmente utilizado

"gemini-2.5-flash"

objectenum<chat.completion>

Tipo de respuesta

"chat.completion"

createdinteger

Marca de tiempo de creación

1760032810

choicesobject[]

Lista de opciones de completado de chat

[
  {
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm pleased to introduce myself.\n\nI'm a Large Language Model, trained and developed by Google.\n\nSimply put, you can think of me as a \"smart brain\" that has been trained on massive amounts of text data and is able to understand and generate human language. My core capability is processing and generating text. Specifically, I can do the following:\n\n**1. Information Query & Knowledge Answering**\nI can act like a \"talking encyclopedia,\" answering various questions, whether they're about scientific knowledge, historical events, or everyday facts.\n\n**2. Creative Writing & Text Generation**\nI can create various types of text based on your requirements, such as:\n*   **Writing**: Poetry, stories, scripts, emails, speeches, advertising copy, etc.\n*   **Planning**: Travel plans, study outlines, event proposals, etc.\n*   **Brainstorming**: Working with you to generate new ideas and spark creativity.\n\n**3. Translation & Language Processing**\nI'm proficient in multiple languages and can provide fast, fluent translation services. I can also help you polish, proofread, summarize, or rewrite text to make your expression clearer and more professional.\n\n**4. Programming & Code Assistance**\nI can write code snippets, explain code logic, debug errors, or \"translate\" code from one programming language to another, making me a helpful companion for programmers.\n\n**5. Logical Analysis & Reasoning**\nI can help you analyze complex problems, organize logical chains, and make inferences and summaries based on the information you provide.\n\n---\n\n**In summary**, my goal is to be a powerful and useful tool that helps you obtain information more efficiently, complete tasks, and spark creativity through natural language communication.\n\n**Remember:** I'm an artificial intelligence, my knowledge comes from the data I've learned, and it may not be the most up-to-date. Sometimes I may also make mistakes, so for very important information, I recommend you verify it again.",
      "tool_calls": [
        null
      ]
    },
    "logprobs": {
      "content": [
        {
          "token": null,
          "logprob": null,
          "bytes": null,
          "top_logprobs": null
        }
      ]
    },
    "finish_reason": "stop"
  }
]

usageobject

Estadísticas de uso de tokens

{
  "prompt_tokens": 13,
  "completion_tokens": 1891,
  "total_tokens": 1904,
  "prompt_tokens_details": {
    "cached_tokens": 0,
    "text_tokens": 13,
    "audio_tokens": 0,
    "image_tokens": 0
  },
  "completion_tokens_details": {
    "text_tokens": 0,
    "audio_tokens": 0,
    "reasoning_tokens": 1480
  },
  "input_tokens": 0,
  "output_tokens": 0,
  "input_tokens_details": null
}

POST/v1/chat/completions

curl --request POST \
  --url https://api.starmagic.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gemini-2.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}'

Respuesta: 成功

{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-2.5-flash",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": null,
        "content": null,
        "tool_calls": null
      },
      "logprobs": {
        "content": [
          null
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

Gemini 2.5 Flash - OpenAI SDK - Inicio rápido

Llamar al modelo gemini-2.5-flash usando el formato del SDK de OpenAI

Modo de procesamiento síncrono, devuelve el contenido de la conversación en tiempo real

Conversación de texto plano: Diálogo de un solo turno o múltiples turnos con contexto, ver ejemplos simple_text y multi_turn en las muestras de código

Prompt del sistema: Personalizar el rol y comportamiento de la IA, ver ejemplo system_prompt en las muestras de código

Entrada multimodal: Soporta entrada mixta de texto + imagen, ver ejemplos vision y multi_image en las muestras de código

[ { "index": 0, "message": { "role": "assistant", "content": "Hello! I'm pleased to introduce myself.\n\nI'm a Large Language Model, trained and developed by Google.\n\nSimply put, you can think of me as a \"smart brain\" that has been trained on massive amounts of text data and is able to understand and generate human language. My core capability is processing and generating text. Specifically, I can do the following:\n\n**1. Information Query & Knowledge Answering**\nI can act like a \"talking encyclopedia,\" answering various questions, whether they're about scientific knowledge, historical events, or everyday facts.\n\n**2. Creative Writing & Text Generation**\nI can create various types of text based on your requirements, such as:\n* **Writing**: Poetry, stories, scripts, emails, speeches, advertising copy, etc.\n* **Planning**: Travel plans, study outlines, event proposals, etc.\n* **Brainstorming**: Working with you to generate new ideas and spark creativity.\n\n**3. Translation & Language Processing**\nI'm proficient in multiple languages and can provide fast, fluent translation services. I can also help you polish, proofread, summarize, or rewrite text to make your expression clearer and more professional.\n\n**4. Programming & Code Assistance**\nI can write code snippets, explain code logic, debug errors, or \"translate\" code from one programming language to another, making me a helpful companion for programmers.\n\n**5. Logical Analysis & Reasoning**\nI can help you analyze complex problems, organize logical chains, and make inferences and summaries based on the information you provide.\n\n---\n\n**In summary**, my goal is to be a powerful and useful tool that helps you obtain information more efficiently, complete tasks, and spark creativity through natural language communication.\n\n**Remember:** I'm an artificial intelligence, my knowledge comes from the data I've learned, and it may not be the most up-to-date. Sometimes I may also make mistakes, so for very important information, I recommend you verify it again.", "tool_calls": [ null ] }, "logprobs": { "content": [ { "token": null, "logprob": null, "bytes": null, "top_logprobs": null } ] }, "finish_reason": "stop" } ]

{ "prompt_tokens": 13, "completion_tokens": 1891, "total_tokens": 1904, "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 13, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 1480 }, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null }

curl --request POST \ --url https://api.starmagic.ai/v1/chat/completions \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "model": "gemini-2.5-flash", "messages": [ { "role": "user", "content": "Please introduce yourself" } ] }'

{ "id": "chatcmpl-20251010015944503180122WJNB8Eid", "model": "gemini-2.5-flash", "object": "chat.completion", "created": 1760032810, "choices": [ { "index": 0, "message": { "role": null, "content": null, "tool_calls": null }, "logprobs": { "content": [ null ] }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 13, "completion_tokens": 1891, "total_tokens": 1904, "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 13, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 1480 }, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null } }