GET

/v1/schemas/replicate/chat/models/google/gemini-2.5-flash/predictions

Accept:

kind inputactivity chathash ecc013bd…extracted Oct 7, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `38a2db8307c8e6a7ee6decd0ec8e1f102f80f5840d2d86baa3b2069ac2f718b4` { "fetchedAt": 1791350061, "extractorVersion": "1", "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 ≤ n ≤ 1 · default: 0.95
images	string[]	Input images to send with the prompt (max 10 images, each up to 7MB)	default: []
prompt*	string	The text prompt to send to the model
videos	string[]	Input videos to send with the prompt (max 10 videos, each up to 45 minutes)	default: []
temperature	number	Sampling temperature between 0 and 2	0 ≤ n ≤ 2 · default: 1
thinking_budget	integer	Thinking budget for reasoning (0 to disable thinking, higher values allow more reasoning)	0 ≤ n ≤ 24576 · default: null
dynamic_thinking	boolean	Enable dynamic thinking - the model will adjust the thinking budget based on the complexity of the request (overrides thinking_budget parameter)	default: false
max_output_tokens	integer	Maximum number of tokens to generate	1 ≤ n ≤ 65535 · default: 65535
system_instruction	string	System instruction to guide the model's behavior	default: null

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"replicate","endpointId":"models/google/gemini-2.5-flash/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}