Sign in
Recipes

ChatCompletion

Changed on

Generate chat completions using language models with support for text and image inputs. /// Compatible with OpenAI Chat Completions API format.

post/v2/consumer/recipes/chatCompletion

Request

  • The document declares no server URL.
  • Auth: none required

Query parameters

experimentalboolean
allowMatureContentboolean
whatifboolean
ephemeralboolean
tier'paid' | 'free'

How a workflow is paid for.

Request body

modelstring required
temperaturenumber double

Temperature for sampling (0-2). Higher values make output more random.

topPnumber double

Nucleus sampling parameter. Consider tokens with top_p probability mass.

maxTokensinteger nullable
thinkingTokenBudgetinteger nullable

vLLM reasoning-token limit per completion, including each server-tool round: 0 ends thinking immediately, -1/null sets no separate limit. MaxTokens still caps thinking plus answer tokens.

reasoningEffortstring nullable

OpenAI reasoning_effort: none, minimal, low, medium, high or xhigh. Portable across vLLM and hosted providers; the worker translates it to each provider's native reasoning control.

ninteger

Number of completions to generate.

stopstring[] nullable

Up to 4 sequences where the API will stop generating tokens.

presencePenaltynumber double

Presence penalty (-2.0 to 2.0). Positive values penalize new tokens based on whether they appear in the text so far.

frequencyPenaltynumber double

Frequency penalty (-2.0 to 2.0). Positive values penalize new tokens based on their existing frequency in the text.

seedinteger nullable
userstring nullable
logprobsboolean nullable
topLogprobsinteger nullable

Number of top log probability candidates to return per generated token. Requires Civitai.Orchestration.Grains.Workflows.Steps.ChatCompletion.ChatCompletionInput.Logprobs to be enabled.

chatTemplateKwargsobject nullable

Model-specific chat template options, forwarded unchanged to vLLM as chat_template_kwargs. Prefer reasoningEffort and thinkingTokenBudget for reasoning control.

tool_choiceunknown
modalitiesstring[] nullable

Output modalities, "text" and/or "image"; defaults to text-only. Including "image" routes the request to the image generation pipeline and returns generated images on the assistant message.

Response

OK

idstring required
objectstring
createdinteger required

Unix timestamp of when the completion was created.

modelstring required
systemFingerprintstring nullable
parsedunknown

Changes