AI/ML API Proxy LLM Configuration

OpenAI-compatible chat completion request schema.

Details can be found in:
https://api.aimlapi.com/docs-public

Parameters

Name	Type	Required	Description
model	string	✅	ID of the model to use.
messages	array	✅	List of messages comprising the conversation.
max_completion_tokens	integer	❌	Maximum number of tokens to generate for completion.
max_tokens	integer	❌	Alias for max_completion_tokens.
stream	boolean	❌	Whether to stream back partial progress.
stream_options	object	❌	Additional options to control streaming behavior.
tools	array	❌	List of tools (functions or APIs) the model may call.
tool_choice	object	❌	Which tool the model should call, if any.
parallel_tool_calls	boolean	❌	Whether tools can be called in parallel.
n	integer	❌	How many completions to generate for each prompt.
stop	array|string	❌	Sequences where the model will stop generating further tokens.
logprobs	boolean	❌	Whether to include log probabilities for tokens.
top_logprobs	integer	❌	Number of most likely tokens to return logprobs for.
logit_bias	object	❌	Modify likelihood of specified tokens appearing in the completion.
frequency_penalty	number	❌	How much to penalize new tokens based on frequency.
presence_penalty	number	❌	How much to penalize new tokens based on whether they appear in the text so far.
seed	integer	❌	Seed for sampling (for reproducibility).
temperature	number	❌	Sampling temperature to use (higher = more random).
top_p	number	❌	Nucleus sampling (top-p) cutoff value.
response_format	object|string	❌	Format to return the completion in, such as 'json' or 'text'.