GET

/v1/schemas/ollama/chat/api%2Fgenerate

kind inputactivity chathash 025a60d2…extracted Nov 10, 2026version currentsource upstream spec ↗

Request body

13 properties · 1 required · 2 $defs
propertytypedescriptionconstraints
model*stringModel name
promptstringText for the model to generate a response from
suffixstringUsed for fill-in-the-middle models, text that appears after the user prompt and before the model response
imagesstring[]
formatstring | objectStructured output format for the model to generate a response from. Supports either the string `"json"` or a JSON schema object.
systemstringSystem prompt for the model to generate a response from
streambooleanWhen true, returns a stream of partial responsesdefault: true
thinkboolean | stringControls a model's thinking output. Use `/api/show` to discover the supported values and default for the selected model. `true` requests thinking, `false` requests no thinking output, and `null` uses the model default. String values are model-defined; supporte…nullable
rawbooleanWhen true, returns the raw response from the model without any prompt templating
keep_alivestring | numberModel keep-alive duration (for example `5m` or `0` to unload immediately)
optionsModelOptionsRuntime options that control text generation
logprobsbooleanWhether to return log probabilities of the output tokens
top_logprobsintegerNumber of most likely tokens to return at each token position when logprobs are enabled

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"ollama","endpointId":"api/generate","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}