#list available openai models

1 messages · Page 1 of 1 (latest)

ionic ridge
#

List latested openai models

kindred hazelBOT
#

Hi @ionic ridge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Here are the latest OpenAI models explicitly listed in the provided sources (grouped by type):

Frontier & general-purpose GPT models

  • GPT-5.2 – best model for coding and agentic tasks across industries [Models]
  • GPT-5.2 pro – higher-precision version of GPT-5.2 [Models]
  • GPT-5 – previous intelligent reasoning model with configurable reasoning effort [Models]
  • GPT-5 mini – faster, cost‑efficient GPT‑5 [Models]
  • GPT-5 nano – fastest, most cost‑efficient GPT‑5 [Models]
  • GPT-4.1 – “smartest non‑reasoning” model [Models]
  • GPT-4.1 mini, GPT-4.1 nano – smaller, faster 4.1 variants [Models]

Reasoning & deep research models

  • o3 – reasoning model for complex tasks [Models]
  • o3-pro – o3 with more compute [Models]
  • o3-deep-research – most powerful deep research model [Models]
  • o4-mini – fast, cost‑efficient reasoning model [Models]
  • o4-mini-deep-research – faster, more affordable deep research model [Models]
#

GPT-4o family & realtime/audio

  • GPT-4o – fast, intelligent, flexible GPT model [Models]
  • GPT-4o mini – small, affordable model [Models]
  • GPT-4o Audio / GPT-4o mini Audio [Models]
  • GPT-4o Realtime / GPT-4o mini Realtime [Models]
  • GPT-4o Transcribe, GPT-4o mini Transcribe, GPT-4o Transcribe Diarize [Models]
  • gpt-realtime, gpt-realtime-mini, gpt-audio, gpt-audio-mini [Models]

Image models

  • GPT Image 1.5 – state‑of‑the‑art image generation [Models]
  • GPT Image 1 – previous image model [Models]
  • gpt-image-1-mini – cost‑efficient GPT Image 1 [Models]
  • chatgpt-image-latest – image model used in ChatGPT [Models]

ChatGPT-specific models (for ChatGPT product)

  • GPT-5.2 chat-latest, GPT-5.1 chat-latest, GPT-5 chat-latest [Models]
  • GPT-5 chat (ChatGPT model), ChatGPT-4o [Models; Models]

Open-weight models

  • gpt-oss-120b – most powerful open‑weight model [Models]
  • gpt-oss-20b – medium open‑weight model [Models]
#

Embeddings & moderation

  • text-embedding-3-large, text-embedding-3-small, text-embedding-ada-002 [Models]
  • text-moderation-latest, text-moderation-stable (deprecated generation) [Models]
  • omni-moderation-latest – multimodal moderation [Models]

Speech & transcription

  • TTS-1, TTS-1 HD – text‑to‑speech [Models]
  • whisper-1 – speech recognition [Models]
  • GPT-4o mini TTS, GPT-4o mini Transcribe, GPT-4o Transcribe (and diarization variant) [Models; Models]

Specialized & video

  • Sora 2, Sora 2 Pro – video generation with synced audio [Models]
  • computer-use-preview – for the Computer Use tool [Models]

Legacy / deprecated examples (still listed)

  • GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, DALL·E 2, DALL·E 3, babbage-002, davinci-002, GPT-4.5 preview (research), etc. [Models; Changelog]
#

For a live, authoritative list (including any models not captured in these static docs), you’d call the Models API GET /models or check the Models page in the dashboard. [API reference; Models]

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: