GET

/v1/schemas/replicate/chat/models/qwen/qwen3-7-plus/predictions

Accept:

kind inputactivity chathash b7213566…extracted Oct 7, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `3ad233949f6260b74906360690018680ccf5d8658041a3455965c16cf1a0ae4f` { "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

image	string[]	Optional list of input images for visual understanding (Qwen3.7-Plus is multimodal). Each image is sent alongside the text prompt.	default: []
top_p	number	A probability threshold for nucleus sampling. Only keeps the top tokens with cumulative probability >= top_p.	0 ≤ n ≤ 1 · default: 0.8
prompt	string	The prompt to send to the model.	default: ""
max_tokens	integer	The maximum number of tokens the model should generate as output.	1 ≤ n ≤ 65536 · default: 2048
temperature	number	The value used to modulate the next token probabilities.	0 ≤ n ≤ 2 · default: 0.7
system_prompt	string	System prompt to guide the model's behavior.	default: "You are a helpful assistant."
presence_penalty	number	Presence penalty. Positive values penalize tokens that have already appeared, encouraging the model to talk about new topics.	-2 ≤ n ≤ 2 · default: 0
frequency_penalty	number	Frequency penalty. Positive values penalize tokens proportionally to how often they have appeared, reducing repetition.	-2 ≤ n ≤ 2 · default: 0

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"replicate","endpointId":"models/qwen/qwen3-7-plus/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}