Get started
Models
Use the ID in the model field. Prices update live; every model has its own page with details, benchmarks and examples.
Chat models
Prices are per 1M input / output tokens. “Reads” is what you can send besides text: see Images, PDFs, audio and video.
Image models
Prices are per image. See Image generation and Image editing.
Video models
Prices are per second of video, by resolution. See Video generation.
Speech models
Prices are per 1M input / output tokens: the text you send, and the audio you get back. See Text to speech.
Embedding models
Prices are per 1M input tokens; the vectors are free. Embedding models turn text into vectors for search and retrieval, on /v1/embeddings. See Embeddings.
Decision models
Prices are per 1M input tokens; the answers are free. Decision models answer typed questions with probabilities instead of writing text. See OpenAI Decisions API for GPT-6 Luna Decisions and Decisions (Jev) for Jev.
Listing models from the API
/v1/modelsReturns every model in OpenAI’s list format, with two extra fields: input_modalities (what the model reads) and, for image models, max_input_images. GET /v1/models/{id} returns one. Neither needs credit.
{ "object": "list", "data": [ { "id": "gemini-3.7-flash", "object": "model", "created": 1790000000, "owned_by": "google", "input_modalities": ["text", "image", "file", "audio", "video"] }, { "id": "nano-banana-pro", "object": "model", "created": 1790000000, "owned_by": "google", "input_modalities": ["text", "image"], "max_input_images": 14 } ]}Retired models
When we retire a model, requests for it get a clear model_not_found error naming the models page. We announce retirements ahead of time where we can.
Questions, or something missing? Ask our support team and we’ll answer by email, usually within a minute.