AI Briefing#ai-gateway
The latest AI and developer news about #ai-gateway, with the original source and a short summary.
The latest AI and developer news about #ai-gateway, with the original source and a short summary.
The model features a 1M-token context window and is designed for coding, multi-step reasoning, and tool-using agents.
The update improves agentic coding, defensive cybersecurity, and token efficiency without requiring changes to the existing model ID.
The feature allows developers to update models and configurations via a single ID, supporting 125 new models added in the last 90 days.
Post-trained on DeepSeek V4.1 Flash, the model targets software engineering tasks with shorter reasoning and fewer tokens.
The feature is in private preview, requiring users to request access from Box and unmount before stopping the sandbox to ensure data persistence.
The partnership covers six audio categories including speech-to-text, streaming TTS, realtime voice agents, music, sound effects, and multi-voice dialogue, accessible via a single API key.
Available on Pro and Enterprise plans with Observability Plus, the feature costs $0.0035 per GB of data scanned and supports alerts via email, Slack, and webhooks.
The model supports configurable reasoning, structured outputs, and tool calling, with a fast mode option for latency-sensitive work.
The new models improve coding, 3D modeling, and financial analysis while maintaining a 1M-token context window and image input capabilities.
The platform uses Vercel Fluid compute for scalable backend processing and AI Gateway to route traffic across multiple model providers to ensure reliability.
Mammoth-1 (27B) and Elephant-1 (9B) offer 16k-token context and return choices, probabilities, and scores for text classification and routing.
The gateway supports providers like OpenAI and Anthropic, protocols like MCP and voice, and features like PII redaction, all as plugins.
The $30/month subscription grants $80 in monthly credit and supports coding agents like fx, Pi, and Cline with Zero Data Retention enabled by default.
The feature handles 15 million connections daily for AI chat and streaming apps, with CPU billed only for active processing time.
The model uses diffusion for parallel text refinement and supports a 1M-token context window for latency-sensitive workloads.
The open-weight multimodal model features a 1M-token context window and improved performance in coding and agentic tasks.
The new view groups requests by session to display cache hit rates, duration, and provider routing paths for coding agents like Claude Code and Codex.
The new model snapshot improves reasoning, coding, and agentic tasks while reducing output tokens and task completion time.
The model accepts images and video to track objects and interpret spatial relationships, accessible via the model name elorian/glimpse.
The new multimodal decision models, Decider V1.2 27B and Decider Flash V1.2 4B, classify content and route requests via typed questions.
Beam is a low-latency open-weight reasoning model with a 1M-token context window and Apache 2.0 license.
The suite unifies server routing, typed data access, and Cloudflare deployment into a single npm package to enable secure internal app shipping.
The multimodal model returns structured probabilities for classification and routing tasks rather than generating text.
The open-weight reasoning model supports text and image input with a 1M-token context window for coding and agentic workflows.