Create a chat completion
llm-gateway.assemblyai.com with llm-gateway.eu.assemblyai.com.Generates a response from a model given a prompt or a series of messages.
Body
Request body for creating a chat completion.
The main request body for the chat completions endpoint.
Optional. The ID of an AssemblyAI transcript whose text replaces the first {{ transcript }} tag in the prompt. See Inject a transcript by ID for substitution rules and edge cases.
"065a71ac-dc3e-4e38-9374-e54c0bea564f"
Optional. The name of one of your account's saved prompts. The stored prompt replaces this request, so the other request fields are ignored, except transcript_id and prompt_replacements. Returns 404 if your account has no prompt with this name. See Saved prompts.
"call-summary"
Optional. Requires aai_prompt. Replaces each {{ key }} tag in the stored prompt with its value. The key transcript is reserved: it's filled from transcript_id, and sending it returns 400. See Saved prompts.
The ID of the model to use for this request. Required unless aai_prompt is set, in which case the model comes from the saved prompt. See LLM Gateway Overview for available models.
"claude-sonnet-4-5-20250929"
Optional. Routes the request to the provider's global (non-region) endpoints for lower-cost processing. The only accepted value is global; omit this field for default in-region processing. Currently live for Anthropic Claude models, with Google Gemini 3 series coming soon.
global "global"
Optional. How much the model reasons before it answers, for models that support it, for example none, low or high. A lower setting is usually faster and cheaper. See Choose a model for the settings each model was benchmarked with.
"low"
An array of fallback objects. Each object must include a model and can optionally override any field from the original request. If the primary model fails, the LLM Gateway tries each fallback in order until one succeeds. See Specify fallback models for more details.
Configuration for fallback behavior, including retry and depth settings. See Specify fallback models for more details.
An ordered list of post-processing steps to apply to the model's response after generation. Currently supports json-repair, which automatically fixes malformed JSON in LLM Gateway content responses. See Post-processing for details.
Response
Successful response containing the model's choices.