Text models
| Model | Slug | Context | Max output | Stream | Tools | JSON | Vision | Files |
|---|---|---|---|---|---|---|---|---|
| Babbage 002 | babbage-002 | 16K | 4K | — | — | — | — | — |
| Codex Mini Latest | codex-mini-latest | 200K | 16K | ✓ | — | — | — | — |
| Computer Use Preview | computer-use-preview | 200K | 16K | ✓ | — | — | — | PDF, images |
| Davinci 002 | davinci-002 | 16K | 4K | — | — | — | — | — |
| GPT Realtime 1.5 | gpt-realtime-1.5 | 200K | 16K | ✓ | — | — | ✓ | PDF, images, audio |
| GPT Realtime Mini | gpt-realtime-mini | 200K | 16K | ✓ | — | — | ✓ | PDF, images, audio |
| GPT-3.5 Turbo | gpt-3.5-turbo | 16K | 4K | ✓ | ✓ | ✓ | — | |
| GPT-4 Turbo | gpt-4-turbo | 128K | 4K | ✓ | ✓ | — | — | PDF, images |
| GPT-4.1 | gpt-4.1 | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-4.1 Mini | gpt-4.1-mini | 200K | 32K | ✓ | ✓ | ✓ | — | PDF, images |
| GPT-4.1 Nano | gpt-4.1-nano | 200K | 16K | ✓ | ✓ | ✓ | — | |
| GPT-4o | gpt-4o | 128K | 16K | ✓ | ✓ | ✓ | ✓ | PDF, images, audio |
| GPT-4o (2024-05-13) | gpt-4o-2024-05-13 | 128K | 4K | ✓ | ✓ | — | — | PDF, images |
| GPT-4o Mini | gpt-4o-mini | 128K | 16K | ✓ | ✓ | ✓ | — | |
| GPT-4o Mini Search | gpt-4o-mini-search-preview | 128K | 16K | ✓ | — | — | — | |
| GPT-4o Search | gpt-4o-search-preview | 128K | 16K | ✓ | — | — | — | |
| GPT-5 | gpt-5 | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5 Codex | gpt-5-codex | 200K | 32K | ✓ | ✓ | — | — | — |
| GPT-5 Mini | gpt-5-mini | 200K | 16K | ✓ | ✓ | ✓ | — | |
| GPT-5 Nano | gpt-5-nano | 200K | 16K | ✓ | ✓ | ✓ | — | |
| GPT-5 Pro | gpt-5-pro | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5 Search API | gpt-5-search-api | 200K | 16K | ✓ | — | — | — | |
| GPT-5.1 | gpt-5.1 | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.1 Codex | gpt-5.1-codex | 200K | 32K | ✓ | ✓ | — | — | — |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 200K | 32K | ✓ | — | — | — | — |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 200K | 16K | ✓ | — | — | — | — |
| GPT-5.2 | gpt-5.2 | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.2 Codex | gpt-5.2-codex | 200K | 32K | ✓ | ✓ | — | — | — |
| GPT-5.2 Pro | gpt-5.2-pro | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.3 Codex | gpt-5.3-codex | 200K | 32K | ✓ | ✓ | ✓ | — | — |
| GPT-5.4 | gpt-5.4 | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.5 | gpt-5.5 | 272K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.5 Pro | gpt-5.5-pro | 272K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.4 Mini | gpt-5.4-mini | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| GPT-5.4 Nano | gpt-5.4-nano | 200K | 16K | ✓ | ✓ | ✓ | — | |
| GPT-5.4 Pro | gpt-5.4-pro | 200K | 32K | ✓ | ✓ | ✓ | ✓ | PDF, images |
| o1 | o1 | 200K | 100K | ✓ | — | — | — | |
| o1-mini | o1-mini | 128K | 64K | ✓ | — | — | — | — |
| o1-pro | o1-pro | 200K | 100K | ✓ | — | — | — | |
| o3 | o3 | 200K | 100K | ✓ | ✓ | — | — | |
| o3 Deep Research | o3-deep-research | 200K | 100K | ✓ | — | — | — | — |
| o3-mini | o3-mini | 200K | 100K | ✓ | ✓ | — | — | |
| o3-pro | o3-pro | 200K | 100K | ✓ | — | — | — | — |
| o4-mini | o4-mini | 200K | 100K | ✓ | ✓ | — | — | |
| o4-mini Deep Research | o4-mini-deep-research | 200K | 100K | ✓ | — | — | — |
Embedding models
| Model | Slug | Max input |
|---|---|---|
| Text Embedding 3 Large | text-embedding-3-large | 8K |
| Text Embedding 3 Small | text-embedding-3-small | 8K |
| Text Embedding Ada 002 | text-embedding-ada-002 | 8K |
Image models
| Model | Slug | Sizes | Max N | Qualities | Styles | Formats | Edits |
|---|---|---|---|---|---|---|---|
| DALL-E 2 | dall-e-2 | 256-1024 | 10 | — | — | png | ✓ (png) |
| DALL-E 3 | dall-e-3 | 1024² to 1792 | 1 | standard, hd | vivid, natural | png | — |
| GPT Image 1 | gpt-image-1 | 1024², 1024×1536, auto | 4 | low-high, auto | — | png, webp, jpeg | ✓ |
| GPT Image 1 Mini | gpt-image-1-mini | 1024², 1024×1536, auto | 4 | low-high, auto | — | png, webp, jpeg | ✓ |
| GPT Image 1.5 | gpt-image-1.5 | 1024², 1024×1536, auto | 4 | low-high, auto | — | png, webp, jpeg | ✓ |
| GPT Image 2 | gpt-image-2 | 1024², 1024×1536, auto | 4 | low-high, auto | — | png, webp, jpeg | ✓ |
Audio models
Text-to-speech
| Model | Slug | Output formats |
|---|---|---|
| GPT-4o Mini TTS | gpt-4o-mini-tts | mp3, opus, aac, flac, wav, pcm |
| TTS-1 | tts-1 | mp3, opus, aac, flac, wav, pcm |
| TTS-1 HD | tts-1-hd | mp3, opus, aac, flac, wav, pcm |
Speech-to-text
| Model | Slug | Response formats | Max file | Inputs |
|---|---|---|---|---|
| GPT-4o Mini Transcribe | gpt-4o-mini-transcribe | json, text, srt, verbose_json, vtt | 25 MB | mp3, mp4, wav, webm, flac, ogg |
| GPT-4o Transcribe | gpt-4o-transcribe | json, text, srt, verbose_json, vtt | 25 MB | mp3, mp4, wav, webm, flac, ogg |
| GPT-4o Transcribe + Diarization | gpt-4o-transcribe-diarize | json, text, srt, verbose_json, vtt | 25 MB | mp3, mp4, wav, webm, flac, ogg |
| Whisper-1 | whisper-1 | json, text, srt, verbose_json, vtt | 25 MB | mp3, mp4, wav, webm, flac, ogg |
Video models
| Model | Slug | Durations | Resolutions | Aspect ratios | Image-to-video |
|---|---|---|---|---|---|
| Sora 2 | sora-2 | 4, 8, 12s | 1280×720, 720×1280 | 16:9, 9:16 | ✓ (jpeg, png, webp) |
| Sora 2 Pro | sora-2-pro | 4, 8, 12s | 1280×720, 720×1280, 1792×1024, 1024×1792 | 16:9, 9:16 | ✓ |