LiteLLM Gateway Adds Fal Video Generation with Per-Clip Cost Tracking
LiteLLM now supports generating videos through Fal via its gateway, with per-clip cost tracking based on length and resolution.
Global AI Digest
-
-
OpenCode Console Tests Agent Event Ingestion from Slack and GitHub
dax says an unreleased console feature lets agents receive events from Slack, GitHub and other sources, with some users already having agents auto-reply to Slac…
-
dax Rewrites OpenCode Browse in Rust, Reimplementing Playwright/Patchright Parts for $60
dax rewrote OpenCode Browse in Rust, reimplementing the parts of Playwright/Patchright they needed, at a cost of only $60.
-
Grok Integrates SpaceXSI Image and Video Creation
Grok is consolidating multiple SpaceXSI products into a single experience, with image and video creation now available directly inside Grok.
-
OpenCode Expands Hardware for DeepSeek, Begins GLM Work
dax reports that additional hardware is now serving DeepSeek with good results, and the team is moving on to figuring out GLM.
-
Cursor Publishes Post-Mortem on Recent Security Incident
Cursor published a detailed overview of a recent security incident along with the remediation steps it has taken.
-
LiteLLM Launches Customer Portal for Usage-Based AI Budgets
LiteLLM released a new Customer Portal that helps teams set budgets for customers, cap spending accurately, and load balance between them for usage-based AI pro…
-
Jev Introduces "Speculative Questions" Batching Pattern
TypeSafe AI shares a Jev best practice: batching questions into a single call even when you don't yet know if you'll need the answers, because it is often faste…
-
Gemini 4 Hydrogen Turns a Simple Brief Into a Finished Video
Gemini 4 Hydrogen can take a short brief and a custom skill to produce a finished video, sourcing public-domain archival footage and assembling it into a single…
-
Tencent's Hy4 Tops CWE-Bench-AA at 76%
Tencent's Hy4 ranks first on CWE-Bench-AA with 76%, six points ahead of DeepSeek V4.1 Flash 1017 (max).
