B
ByteDance Seed 1.8
BytePlus
🧠 Language Model
ByteDance Seed 1.8, multimodal agent model (text, image & video in → text), strong tool use + reasoning, 256K context. Native via BytePlus (Ark).
Specifications
ModalitiesInput: text, image, video · Output: text
Context window262K tokens
Max output65K tokens
Speed●●●○○ Average
FeaturesTools: Yes Streaming: Yes Vision: Yes
Capabilitiestools, reasoning
Pricing
$0.4375 / 1M input tokens · $3.50 / 1M output tokens
Platform credit pricing — live rates on the Models page.