Tag
This article explains the cost factors for tasks on Opus 5.5, detailing how turns, cache reads, output tokens, and model selection influence token expenses.
The tweet discusses the distribution challenges of open AI models and highlights how Bolt Forge integrates multiple models, with usage statistics showing GLM 5.3 Flash leading due to latency and cost advantages.
This tweet discusses the closing gap between open and closed AI models, with bolt.new reporting popular usage of models like GLM 5.3 Flash and DeepSeek V4 Pro among builders.
This post discusses the recent release of the K2-Horizon-MoVA-36B-A4B MoE model and asks about its current usage and potential use cases, providing a link to model comparisons.
The article recommends using GPT-6 Astra by breaking tasks into steps, starting with medium settings to replicate a demo and then using max settings to optimize results, leveraging subagents for efficiency.
The article suggests that using gpt-image-2 in a iterative loop to refine designs produces superior outcomes compared to generating designs from scratch.
The author believes that in harness, low-capability flash models are more suitable for management tasks, while the agents doing the real work should use advanced models like sol and fable.
Comparison of monthly token volume shares by model author between January 2026 and June 2026, as of June 14th.
An analysis of OpenRouter data shows that US and Chinese companies train nearly all of the world's most-used AI models, with Chinese models rapidly increasing to 20 out of the top 50 by May 2026.
When several AI models were priced equally for a week, actual token usage revealed preference differences from leaderboard rankings, showing that coding and general chat have different top models and long context usage concentrated on two trusted models.