Seed 2.1 Lite
字节跳动 · Text
Omnimodal ByteDance Seed 2.1 model with native text, vision, and audio understanding, 1M context, and improved coding and agent task completion
Model ID bytedance/seed-2.1-liteUpdated Sep 15, 2026
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input—No public pricing—No public pricing
Output—No public pricing—No public pricing
Cache read—No public pricing—No public pricing
Cache write—No public pricing—No public pricing
Specifications
- Form
- Text model
- Input modalities
- Text、Image、Audio、Video
- Output modalities
- Text
- Context length
- 1M
- Max output
- 256K
- Weights
- Closed
- Family
- seed
- Released
- Sep 15, 2026
Uses and capabilities
Capabilities Text model、Function calling、Reasoning
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.