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 (only { "type": "json_object" } or { "type": "text" } — OpenAI's json_schema / Strict Structured Outputs is not currently supported)
stream
temperature
tools
tool_choice
Reasoning effort/level (e.g. OpenAI's reasoning_effort) cannot currently be set via the API — reasoning models use their default effort level for API requests.
Message content must be a plain text string — the API does not currently accept images, files, or other attachments (e.g. image_url content blocks) in chat completion requests. To send files or images, use the Assistants Run or Workflow execution API instead.
Note
For schema-validated JSON output without OpenAI's json_schema mode, define a tool whose parameters are the JSON Schema you want and set tool_choice to that function ({"type": "function", "function": {"name": "..."}}). The model is then required to call the function with arguments matching the schema — read the JSON from tool_calls[0].function.arguments instead of content.
Note
Reasoning-tier models use a fixed internal temperature and may reject other values. If you get an error with these models, try omitting temperature from your request or removing any client-side default.
Note
Not every model you see in meinGPT chat is automatically usable via the API. Which models are enabled for your organization is set by a workspace admin (see Workspace Configuration).
Call GET /models/v1 to retrieve the exact list of models enabled for your API key, and use the value from the id field verbatim as model in your request.
If you send a model value that isn't enabled for your organization, the API responds with 403 Forbidden and an error message of this form:
{ "status": "error", "message": "Model 'your-model-id' is not enabled for this organization."}
This message is distinct from the general 403 error "completions API not enabled for organization" (which affects the entire completions API, not a single model). Free-tier models (currently GPT-5 Nano, API id gpt-5-nano) are exempt from this restriction and are always available.
Creates a model response for the given chat conversation. Compatible with OpenAI's chat completions API.
🔒 ApiKeyAuth
Parameter
Parameter
In
Typ
Beschreibung
Authorization*
header
string
API key for authentication. Use 'Bearer <your-api-key>' format.
Request Body · application/json
Feld
Typ
Beschreibung
messages*
Array<ChatMessage>
List of messages comprising the conversation so far
model*
string
ID of the model to use
response_format
object
stream
boolean
Whether to stream back partial progress
temperature
number
Sampling temperature to use
tools
Array<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" | object
Controls which tool is called — 'auto', 'none', 'required', or a specific function.
Responses
200Successful response
Feld
Typ
Beschreibung
id
string
Unique identifier for the chat completion
object
string
created
number
Unix timestamp
model
string
The model used
choices
Array<object>
usage
Usage
400Bad request - invalid input
Feld
Typ
Beschreibung
status
string
message
string
401Unauthorized - missing or invalid API key
Feld
Typ
Beschreibung
status
string
message
string
403Forbidden - completions API not enabled for organization