docs/sample-provider-configs/openai.yml

base_url: https://api.openai.com/v1
api_key: YOUR_API_KEY_HERE
text_generation:
  model_id: gpt-5.4
  prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
  temperature: 1.0
  # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
  # If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`.
  max_response_tokens: null
  max_completion_tokens: 128000
  max_context_tokens: 400000
  # Built-in tools
  tools:
    web_search: false
    code_interpreter: false
speech_to_text:
  model_id: whisper-1
text_to_speech:
  model_id: tts-1-hd
  voice: onyx
  speed: 1.0
  response_format: opus
image_generation:
  model_id: gpt-image-2
  style: null
  size: null
  quality: null
Initial commit 2024-09-12 13:44:06 +03:00			`base_url: https://api.openai.com/v1`
			`api_key: YOUR_API_KEY_HERE`
			`text_generation:`
Bump default OpenAI text-generation model (`gpt-5.2` -> `gpt-5.4`) 2026-03-11 09:53:02 +02:00			`model_id: gpt-5.4`
Allow for prompt caching to work by using `baibot_conversation_start_time_utc` instead of `baibot_now_utc` This patch introduces a new `baibot_conversation_start_time_utc` variable which indicates the time the conversation got started. Using `baibot_now_utc` is still possible, but given that the current time is a moving target, its use is in conflict with prompt caching. Because the new `baibot_conversation_start_time_utc` prompt variable is a more reasonable default, we're now using it in all sample configs. 2024-10-03 11:48:14 +03:00			`prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."`
Initial commit 2024-09-12 13:44:06 +03:00			`temperature: 1.0`
Update sample OpenAI config (for `gpt-5`) misleading users into using `max_response_tokens` & remove `openai-o1.yml` sample config No need to have both sample configs now. Fixes https://github.com/etkecc/baibot/issues/57 2025-11-20 05:22:24 +02:00			# Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
			# If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`.
			`max_response_tokens: null`
			`max_completion_tokens: 128000`
			`max_context_tokens: 400000`
Implement OpenAI's response API and add support for built-in tools (web search & code interpreter). 2026-01-23 22:05:53 +01:00			`# Built-in tools`
			`tools:`
			`web_search: false`
			`code_interpreter: false`
Initial commit 2024-09-12 13:44:06 +03:00			`speech_to_text:`
			`model_id: whisper-1`
			`text_to_speech:`
			`model_id: tts-1-hd`
			`voice: onyx`
			`speed: 1.0`
			`response_format: opus`
			`image_generation:`
Default to gpt-image-2 for OpenAI image generation Make gpt-image-2 the default image-generation model and add it to the recognized model-id mapping, updating the sample provider configs to match. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> 2026-06-05 09:39:45 +03:00			`model_id: gpt-image-2`
Default OpenAI image-generation model to `gpt-image-1` (previously `dall-e-3`) 2025-05-03 09:41:54 +03:00			`style: null`
Allow `image_generation.size` to be `null` for OpenAI and default it to that The API spec for image creation and image editing says "string or null", so we're allowing `null` now to trigger automatic selection. 2025-05-11 23:18:19 +03:00			`size: null`
Default OpenAI image-generation model to `gpt-image-1` (previously `dall-e-3`) 2025-05-03 09:41:54 +03:00			`quality: null`