ai-gateway

Flash models, cheaper inference, new integrations

Grok 4.6 + Mojo 1.0: Agent routing reshapes API layers

Claude Agents + Chat SDK, Gemini cuts tokens 17%

Grok 4.5 launches; Vercel expands agent tooling

Vercel Connect GA + Claude Desktop Ollama Support

Grok audio on Vercel, Go 1.26 green GC, voice APIs

Open models surge: Qwen, DeepSeek, Moonshot updates

GPT-5.6 costs drop 80%; Claude context fees slash 97.6%

Gemini 3.7 Flash: 50% off + STT quality metrics

Bun 1.4 rewrites runtime, Next.js cuts memory 90%

GLM 5.2 Fast + Gemini's Computer Use: Week's Dev Wins

MCP 2.0 + Security Patches: Rails RCE, Nuxt Updates

Gemini 3.6 Flash: 17% fewer tokens

Gateway Rush: GLM-5.3 Flash, Gemini Transcribe, Qwen 3.8

Vercel + Lovable, GPT-5.6 multiagent, curl security patch

Opus 5 on AI Gateway, Ruff v0.16 ships 413 rules

Terminal agents + 975B models: Weekly signals

Gemma 4 multimodal agents + Claude Fable 5 GA

Muse Spark 1.1 + GPT-5.6 launches; Rust 1.97 ships

Node.js Security Patches + AI Agent Updates

AI deploys code via chat, Node.js patches live

Gateway routing, agents ship, Mistral TTS drops

Sandbox forking, million-token models, agent budgets

Vector search lands in DynamoDB natively

Inkling MoE + Agent Safety: Token Efficiency Meets Reliability

Claude Design + Vercel, WebSocket Functions, on-device AI

Azure DeepSeek routing + sparse attention, local diffusion

Video gen, AWS models, prompt injection risks

Claude Opus 4.8: 4x fewer agent errors, same cost