GET

/v1/schemas/replicate/chat/models/deepseek-ai/deepseek-v3.1/predictions

Accept:

kind inputactivity chathash 315a737b…extracted Oct 7, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `fa3e6c9f610f602c1dce9e067a2eefe08faad16c38f022ade408b453026efc54` { "fetchedAt": 1791350061, "extractorVersion": "1", "verifiedAt": null }

Request body

4 properties · 1 required · 2 $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

2 $defs

Inputobject

top_p	number	Top-p (nucleus) sampling	default: 1
prompt	string	Prompt	default: "Why are you better than Deepsee…
thinking	enum	An enumeration.	medium \| None
max_tokens	integer	The maximum number of tokens the model should generate as output.	default: 1024
temperature	number	The value used to modulate the next token probabilities.	default: 0.1
presence_penalty	number	Presence penalty	default: 0
frequency_penalty	number	Frequency penalty	default: 0

thinkingenum

An enumeration.

medium | None

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"replicate","endpointId":"models/deepseek-ai/deepseek-v3.1/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}