GET

/v1/schemas/anthropic/chat/v1/complete

Accept:

kind inputactivity chathash 532673b8…extracted Oct 15, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `05e92b686382eeac1d8070f9f2aaf5fa8180e804b1b9fa1f498b70a0325b898c` { "fetchedAt": 1792041619, "extractorVersion": "1", "verifiedAt": null }

Request body

9 properties · 3 required · 2 $defs

property	type	description	constraints
model*	string	The model that will complete your prompt.	20 known values
prompt*	string	The prompt that you want Claude to complete.	length ≥ 1
max_tokens_to_sample*	integer	The maximum number of tokens to generate before stopping.	n ≥ 1
stop_sequences	string[]	Sequences that will cause the model to stop generating.
temperature	number	Amount of randomness injected into the response.	0 ≤ n ≤ 1 · deprecated
top_p	number	Use nucleus sampling.	0 ≤ n ≤ 1 · deprecated
top_k	integer	Only sample from the top K options for each subsequent token.	n ≥ 0 · deprecated
metadata	Metadata	An object describing metadata about the request.
stream	boolean	Whether to incrementally stream the response using server-sent events.

Types

2 $defs

Metadataobject

user_id

string

An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.

length ≤ 512 · nullable

Modelstring

The model that will complete your prompt.

20 known values

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"anthropic","endpointId":"v1/complete","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}