model field on your request.
Modalities
Text (LLMs)
GPT, Claude, Gemini, DeepSeek, Grok and more. Chat and reasoning.
Image
FLUX, Nano Banana, Ideogram, Seedream and more. Generate and edit.
Video
Kling, Seedance, Veo and more. Text-to-video and image-to-video.
Audio
Speech-to-text and text-to-speech.
Listing models
Fetch the live list of models and their prices:id (what you pass in requests), its name,
modality, and pricing. See List models.
Choosing a model
- Text: balance quality vs cost. Cheaper models are great for simple tasks; frontier models for hard reasoning.
- Image / video: pick by style and speed. Prices vary widely by resolution and length.