跳转到主要内容
2026/7/21 12:22 (UTC+8) · New Model · ByteDance 🚀 Seed 2.1 Turbo is live — both endpoints verified 15/15 ByteDance’s high-frequency production text model dola-seed-2-1-turbo-260628 (released 6/23) is now available on the default / svip groups at $0.50 input / $2.50 output per 1M tokens. Both Chat Completions and Responses passed the full test suite: structured output, two-turn function calling, thinking toggle and tiers, and implicit + explicit two-layer caching are all verified. Note that deep thinking is ON by default — pass thinking: {"type": "disabled"} for high-frequency short Q&A to save cost and latency. Deep dive: Seed 2.1 Turbo Launch; onboarding and playgrounds: Model Overview.
Back to Live · 📚 Monthly Archive