Chat Completion

OpenAI's ChatCompletion API
Supports all OpenAI Chat models, including the latest versions
For detailed parameters about this API, you can refer to OpenAI's official documentation: https://platform.openai.com/docs/api-reference/chat/create
You can also use this API to call many non-OpenAI models in the format of OpenAI's ChatCompletion API, such as Anthropic's Claude series models, TA, ChatGLM, Cohere, etc. For the specific list of supported models, please refer to the model list on the website settings page, as the content in the documentation may not be maintained in a timely manner

Gemini Pro Vision Usage Example

You can completely refer to OpenAI's Vision guide: https://platform.openai.com/docs/guides/vision
Example input:

{
    "model": "gemini-pro-vision",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text", "text": "Describe this image"
                },
                {
                    "type": "image_url",
                    "image_url": "https://pbs.twimg.com/media/GBEB1CbbIAAC28o?format=jpg&name=small"
                }
            ]
        }
    ],
    "stream": false
}

Note: It also supports Base64 as image input, and Base64 has higher reliability. Base64 is recommended. The link is used here to avoid excessive word count.
Response result:

{
  "id": "chatcmpl-gPyHaMj77C8Uca3UudUL5zxvAvI3N",
  "object": "chat.completion",
  "created": 1702560711,
  "model": "gemini-pro-vision",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": " These are emoticons of five different characters. They are:\n- Hu Tao\n- Yao Yao\n- Sayu\n- Keqing\n- Sangonomiya Kokomi"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 48,
    "total_tokens": 56
  }
}

Streaming request ("stream": true) response result:

data: {"id":"chatcmpl-6tzfeCctklU06xs8BmDo3b1YcCold","object":"chat.completion.chunk","created":1702562069,"model":"gemini-pro-vision","choices":[{"index":0,"delta":{"role":"assistant","content":" These are emoticons of five different characters. They are:\n- Hu Tao\n- Yao Yao\n- Sayu\n- Keqing\n- Sangonomiya"},"finish_reason":null}]}
data: {"id":"chatcmpl-6tzfeCctklU06xs8BmDo3b1YcCold","object":"chat.completion.chunk","created":1702562069,"model":"gemini-pro-vision","choices":[{"index":0,"delta":{"role":"assistant","content":" Kokomi"},"finish_reason":null}]}
data: [DONE]

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/json

model

string

required

messages

array [object {2}]

required

role

string

required

content

string

required

stream

boolean

required

Example

{
    "model": "gpt-3.5-turbo",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Say test"
        }
    ],
    "stream": false
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Body

object {0}

Examples

Success(NonStream)Success(Stream)

{
    "id": "chatcmpl-8Je5EIkoizgX7HIZHCfak05B9YmYx",
    "object": "chat.completion",
    "created": 1699693004,
    "model": "gpt-3.5-turbo-1106",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Test"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 19,
        "completion_tokens": 1,
        "total_tokens": 20
    },
    "system_fingerprint": "fp_eeff13170a"
}

Gemini Pro Vision Usage Example#

Request

Request samples

Responses

Gemini Pro Vision Usage Example