Vision Interface [Chat Compatible Format]

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. Create a completion for the provided prompt and parameters Official Documentation: https://ai.google.dev/gemini-api/docs/image-understanding?hl=zh-cn

Endpoint

POST http://v98store.com/v1/chat/completions

cURL Command

curl -X POST 'http://v98store.com/v1/chat/completions' \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer YOUR_TOKEN' \ -d '{ "model": "gemini-1.5-pro-latest", "stream": false, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "this张图片Yes什么" }, { "type": "image_url", "image_url": { "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png" } } ] } ], "temperature": 0.9, "max_tokens": 400 }'

Parameters

Request Body

Example

{
  "model": "gemini-1.5-pro-latest",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "this张图片Yes什么"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
          }
        }
      ]
    }
  ],
  "temperature": 0.9,
  "max_tokens": 400
}

Responses

200 -

Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}