Doubao Work adds Kimi K3.1 Pro, GLM 5.3, DeepSeek V4.1 Flash with cheaper token multipliers
xiaohu · x · 2026-11-12
ByteDance's Doubao Work has opened up third-party model access, adding Kimi K3.1 Pro, GLM 5.3, DeepSeek V4.1 Flash and more, letting users pick different models for different task levels — echoing how Codex now works with any open model.
Doubao Work also launched limited-time discounts lowering the credit-consumption multipliers for Doubao 2.1 Lite and DeepSeek V4.1 Flash, and labels each model with its cost multiplier; the author's tests show consumption notably lower than the models' official platforms. The takeaway: in the agent era, tasks are more varied and chains longer, so multi-model freedom beats single-model lock-in.
More from Models
- MiniMax H3-Image tops both Artificial Analysis open-weight image leaderboards — socialwithaayan · 2026-11-12
- Nanbeige4.3-33B beats Claude Opus 5 on AutomationBench, 54.2 to 50.3 — NielsRogge · 2026-11-12
- Gemini 4 Hydrogen spotted in Google Cloud billing catalogue, priced near Opus 5.5 level — imjustnewatai · 2026-11-12
- Ant's Ling-3.2-flash: 560B/25B active multimodal model beats Opus 5 on vision benchmarks — Med1_Ai · 2026-11-12
- Leak: xAI Working on a Selection Box for Grok Bot to Comment on Files — nima_owji · 2026-11-12
- Baidu opens API access to ERNIE 5.5 Flash Preview — Baidu_Inc · 2026-11-12