Skip to main content
Method: CompletionsApi#create_chat_completion.

​
Example

require 'ai_stats_sdk'

config = AIStatsSdk::Configuration.default
config.access_token = 'your_api_key'
api_client = AIStatsSdk::ApiClient.new(config)
completions_api = AIStatsSdk::CompletionsApi.new(api_client)

request = AIStatsSdk::ChatCompletionsRequest.new(
  model: 'openai/gpt-4o-mini',
  messages: [
    AIStatsSdk::ChatMessageUser.new(content: 'Write a limerick about lighthouses.', role: 'user')
  ],
  temperature: 0.5
)

response = completions_api.create_chat_completion(request)

​
Key parameters

  • model (required): Target model id.
  • messages (required): Ordered messages with roles user/system/assistant/tool; content as strings.
  • Sampling: temperature (0–2), top_p (0–1), top_k (>=1), seed (int, optional).
  • Length/penalties: max_output_tokens (int), presence_penalty and frequency_penalty (-2 to 2), stop (string|string[]).
  • Tools: tools (definitions), tool_choice (auto/none/specific tool), max_tool_calls (int), parallel_tool_calls (bool).
  • Logprobs: logprobs (bool), top_logprobs (0–20).
  • Output: response_format (json/text), metadata (object passthrough), stream (bool), service_tier.
  • Gateway extras: usage (bool to request usage), meta (bool to include meta block).

​
Returns

ChatCompletionsResponse