Seed-2.0-Mini
Seed-2.0-Mini from Bytedance targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It supports 256k context, four reasoning effort modes, and multimodal understanding (including image and video), and is optimized for lightweight tasks where cost and speed take priority.
This model is served from Malaysia.
Note: Pricing is 2x when input tokens >=128k
Parameter controls available:
1. Reasoning
- Default: Thinking enabled
- Reasoning effort [low, medium, high]: How deeply the model thinks. Low=fast, Medium=balanced, High=thorough (default: medium). Only applies if thinking is enabled.
2. Search & Vision
- Web Search: Enable real-time web search for up-to-date information (default: false).
- Image Detail [low, high, xhigh]: Quality for image understanding. Higher = more accurate but uses more tokens (default: high).
- Video FPS [0.2-5]: Frame sampling rate for video input. Higher = more frames analyzed, more accurate, more tokens (default: 1).
Powered by a server managed by @empiriolabsai. Learn more
Build with Seed-2.0-Mini using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from Empirio Labs AI
New
Seedance-2.0-Fast-EL
New
Seedance-2.0-Pro-EL
New
DeepSeek-V3.2-EL
Wan-2.7
Qwen3.6-Plus
Wan2.7-Image
Qwen3.5-Omni-Flash
Qwen3.5-Omni-Plus
Seed-2.0-Pro
MiMo-V2-Omni