ByteDance
ByteDance through your own BytePlus ModelArk API key and its REST API, covering text and tool-calling chat, images and video, with models such as the Seed family, Seedream and Seedance. Requests go straight from your machine to ModelArk and you pay ByteDance's own rates; Seedance 2 needs a funded ModelArk account.
Text(5 models)
ByteDance's fast Seed 2.1 reasoning model with a 256K context and output window, native tool calling and image input.
Balanced Seed 2.0 reasoning model with tool calling and image input at a lower price than Pro.
The smallest, cheapest Seed 2.0 model for fast everyday tasks, with tool calling and image input.
Preview of ByteDance's coding-tuned Seed 2.0 model for code generation and agentic programming, with tool calling.
ByteDance's flagship Seed 2.0 reasoning model for complex analysis, coding and agentic tool use, with image input and a 256K context.
Image(4 models)
ByteDance's fast, low-cost Seedream 5 tier for high-volume image generation and editing, with multi-reference input.
ByteDance's flagship Seedream 5 model — top-tier aesthetic quality, prompt fidelity, and multi-reference editing up to 2K.
Lightweight Seedream variant for fast, high-quality image generation.
ByteDance's versatile image model with strong aesthetic quality and prompt fidelity.
Video(4 models)
ByteDance's flagship multimodal video model — native synchronized audio, clips up to 30 seconds, and large reference sets for character and scene consistency.
ByteDance's lightweight Seedance 2.0 tier — about half the cost per second, 480p/720p with synchronized audio.
ByteDance's low-latency Seedance 2.0 tier — quick 480p/720p generation with synchronized audio.
ByteDance's advanced video model with improved motion coherence and scene quality.