Skip to main content
POST
https://gptproto.com
/
v1
/
chat
/
completions
kimi-k2.5 (Text to Text)
curl --request POST \
  --url https://gptproto.com/v1/chat/completions

​
Authentication

  1. Sign up for a GPTProto account at https://gptproto.com
  2. Navigate to the API Keys section in your dashboard
  3. Generate a new API key (sk-xxxxx)
  4. Copy and securely store your API key For authentication details, please refer to the Authentication section.

​
Initiate Request

curl --location 'https://gptproto.com/v1/chat/completions' \
--header 'Authorization: GPTPROTO_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
  "model": "kimi-k2.5",
  "messages": [
    {
      "role": "user",
      "content": "Who are you?"
    }
  ],
  "stream": false
}'

​
Parameters

​
Core Parameters

ParameterTypeRequiredDefaultRangeDescription
modelstring✅ Yes--Model ID used to generate the response, like kimi-k2.5.
messagesarray✅ Yes--A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and files.
>messages.rolestring✅ Yes-system
user
assistant		The role of the messages author.
>messages.contentstring / array✅ Yes--The contents of the message. Can be a string for text-only messages or an array for multimodal content.
>>messages.content.typestring✅ Yes-text
image_url
file		The type of the content part.
>>messages.content.textstring❌ No--The text content.
>>messages.content.image_urlobject❌ No--The image URL content.
>>messages.content.image_url.urlstring❌ No--The URL of the image.
>>messages.content.fileobject❌ No--The file content for document analysis.
>>messages.content.file.filenamestring❌ No--The name of the file.
>>messages.content.file.file_datastring❌ No--The URL of the file.

​
Advanced Parameters

ParameterTypeRequiredDefaultRangeDescription
max_tokensinteger❌ No--The maximum number of tokens to generate in the response.
temperaturenumber❌ No0.950.0 - 1.0Controls randomness. Lower values make the model more focused and deterministic.
top_pnumber❌ No0.70.0 - 1.0Nucleus sampling parameter. The model considers the results of the tokens with top_p probability mass.
streamboolean❌ Nofalsetrue
false		Whether to stream the response back incrementally using server-sent events.
toolsarray❌ No--A list of tools the model may call. Use this to enable web search or function calling capabilities.
stoparray❌ No--Up to 4 sequences where the API will stop generating further tokens.

​
Response Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699896916,
  "model": "kimi-k2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am Kimi K2.5, a large language model developed by Moonshot AI. I'm designed to assist with a wide range of tasks including answering questions, writing content, analyzing documents, and more."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 45,
    "total_tokens": 57
  }
}

​
Error Codes

​
Common Error Codes

Error CodeError NameDescription
401UnauthorizedAPI key is missing or invalid
403ForbiddenYour API key doesn’t have permission to access this resource, or insufficient balance for the requested operation
429Too Many RequestsYou’ve exceeded your rate limit
500Internal server errorAn internal server error occurred
503Content policy violationContent blocked due to safety concerns (actual status code is 400)