Completions

OpenAI-compatible API endpoints

Achtung

Our API does not support all parameters offered by OpenAI. Requests are still accepted and processed, but not all parameters are considered.

Supported parameters:

  • model
  • messages
  • response_format
  • stream
  • temperature
  • tools
  • tool_choice
posthttps://app.meingpt.com/api/openai/v1/chat/completions

Create a chat completion

Creates a model response for the given chat conversation. Compatible with OpenAI's chat completions API.

🔒 ApiKeyAuth

Parameter

ParameterInTypBeschreibung
Authorization*headerstringAPI key for authentication. Use 'Bearer <your-api-key>' format.

Request Body · application/json

FeldTypBeschreibung
messages*Array<ChatMessage>List of messages comprising the conversation so far
model*stringID of the model to use
response_formatobject
streambooleanWhether to stream back partial progress
temperaturenumberSampling temperature to use
toolsArray<object>Tools (functions) the model may call. Not every model supports tool calling — a request with tools against an unsupported model (e.g. Perplexity) returns 400.
tool_choice"auto" | "none" | "required" | objectControls which tool is called — 'auto', 'none', 'required', or a specific function.

Responses

200Successful response
FeldTypBeschreibung
idstringUnique identifier for the chat completion
objectstring
creatednumberUnix timestamp
modelstringThe model used
choicesArray<object>
usageUsage
400Bad request - invalid input
FeldTypBeschreibung
statusstring
messagestring
401Unauthorized - missing or invalid API key
FeldTypBeschreibung
statusstring
messagestring
403Forbidden - completions API not enabled for organization
FeldTypBeschreibung
statusstring
messagestring
500Internal server error
FeldTypBeschreibung
statusstring
messagestring
Was this page helpful?