Seed-2.0-Mini
Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...
The figures
- Made by
- ByteDance Seed
- Model ID
- bytedance-seed/seed-2.0-mini
- Input
- $0.1 per million tokens
- Output
- $0.4 per million tokens
- Context window
- 262K tokens
- Longest answer
- 131K tokens
- Takes in
- text, image, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- No
- Released
- 26 Feb 2026
Read on 3 Oct 2026.