GET

/v1/schemas/replicate/chat/models/openai/gpt-4.1-mini/predictions

Accept:

kind inputactivity chathash cd30fa71…extracted Nov 11, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `72d2e792835d9344a1b4a8765f49dac55d686a04533709e64157c851047c4f56` { "fetchedAt": 1794375035, "extractorVersion": "2", "verifiedAt": null }

Request body

4 properties · 1 required · 1 $defs

property	type	description
input*	Input
stream	boolean	This field is deprecated.
webhook	string	An HTTPS URL for receiving a webhook when the prediction has new output. The webhook will be a POST request where the request body is the same as the response body of the [get prediction](#predictions.get) operation. If there are network problems, we will retr…
webhook_events_filter	enum[]	By default, we will send requests to your webhook URL whenever there are new outputs or the prediction has finished. You can change which events trigger webhook requests by specifying `webhook_events_filter` in the prediction request:

Types

1 $defs

Inputobject

top_p	number	Nucleus sampling parameter - the model considers the results of the tokens with top_p probability mass. (0.1 means only the tokens comprising the top 10% probability mass are considered.)	0 ≤ n ≤ 1 · default: 1
prompt	string	The prompt to send to the model. Do not use if using messages.
messages	object[]	A JSON string representing a list of messages. For example: [{"role": "user", "content": "Hello, how are you?"}]. If provided, prompt and system_prompt are ignored.	default: []
image_input	string[]	List of images to send to the model	default: []
temperature	number	Sampling temperature between 0 and 2	0 ≤ n ≤ 2 · default: 1
system_prompt	string	System prompt to set the assistant's behavior
presence_penalty	number	Presence penalty parameter - positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.	-2 ≤ n ≤ 2 · default: 0
frequency_penalty	number	Frequency penalty parameter - positive values penalize the repetition of tokens.	-2 ≤ n ≤ 2 · default: 0
max_completion_tokens	integer	Maximum number of completion tokens to generate	default: 4096

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"replicate","endpointId":"models/openai/gpt-4.1-mini/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}