Skip to main content
Search

Vercel

38 related articles

Subscribe to updates
  1. Vercel News

    Vercel's AI Gateway adds Private Inference: self-hosted and fine-tuned models now share one key, SDK and log

    Vercel's AI Gateway has added Private Inference, which connects enterprise self-hosted, fine-tuned or prerelease models as private providers. Such models previously needed separate keys, client code and logs; they now share the same authentication, SDKs, APIs and observability as catalog models, and switching only changes the model ID to private/<slug> while the gateway translates each request to the endpoint's format. Private models are visible only to their team, stay out of the public catalog, store credentials encrypted, and can enable Zero Data Retention per provider.

  2. Vercel News

    Tencent's Hy4 Flash lands on AI Gateway: full Hy4 feature set at roughly a tenth of the per-token price

    Tencent's Hy4 Flash is now callable through AI Gateway, with an introductory 50% discount on input, cached input and output tokens through November 29, 2026. It is the lower-cost model in the Hy4 family, keeping the full Hy4 feature set at roughly a tenth of the per-token price: reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching and image input, with the same 1M-token context window. Reasoning can be turned off for requests that don't need it, suiting high-volume coding, agent and document workloads.

  3. Vercel News

    Vercel's Workflow SDK now writes events and streams over WebSockets, delivering an AI agent's token stream 4.2× faster

    Starting with version 5.2.0, Vercel's Workflow SDK sends event writes and stream writes to Vercel Workflows over a WebSocket by default, replacing one HTTP request per write, or per write group for streams, with no code change beyond the upgrade. In a benchmark replaying an AI agent's token stream, v5.2.0, which writes streams over a WebSocket by default, delivered the full response 4.2× faster than v4.8.12, with no chunk delayed over a second.

  4. Vercel News

    Gemini 4 Carbon lands on AI Gateway: a 1M-token context and half-price calls through November 30, 2026

    Google's Gemini 4 Carbon is now available on AI Gateway under the model name google/gemini-4-carbon, aimed at complex software engineering, sustained agentic work and cybersecurity defense, with a 1M-token context window for large codebases and long inputs. Google reports improvements in coding, full-stack web development and scientific reasoning on multi-stage engineering tasks, cybersecurity coverage from finding vulnerabilities through validating risk to developing patches, and more reliable multi-step plan execution, fewer unsupported claims and better collaboration when requirements are ambiguous. Calls through AI Gateway reflect provider pricing with no markup and no platform fee on inference, at 50% off through November 30, 2026.

  5. Vercel News

    Google's Gemini 4 Hydrogen lands on AI Gateway: stronger agentic coding and tool use, same latency class

    Google's Gemini 4 Hydrogen is now available on AI Gateway, succeeding Gemini 3.8 Flash. It targets agentic coding, knowledge work and tool use, handling longer engineering tasks and producing better-researched documents, spreadsheets and presentations in fewer agent steps while staying in the same latency class. It follows system instructions, formatting requirements and task boundaries more closely, orchestrates tools more reliably across long conversations, and its gains in visual reasoning and technical problem-solving support multimodal workflows.

  6. Vercel News

    Claude Fable 5.2 lands on AI Gateway: it runs long tasks unattended and hands simpler work to smaller models

    Anthropic's Claude Fable 5.2 is now callable through AI Gateway, built for open-ended technical work and improving on earlier Fable models in coding, reasoning and vision, and able to run long, ambiguous tasks unattended. It can act as an orchestrator that hands simpler tasks to smaller models, or as an advisor other Claude models consult on harder problems, with clearer communication and faster output. The model ships with cybersecurity and biology safety classifiers, and access requires data retention: prompts and completions are kept for 30 days and not used to train Claude, while teams with Zero Data Retention enabled get an error instead of a forwarded request.

  7. Vercel News

    Mistral Large 4 gets new weights on AI Gateway: same model ID, lower input, cached-input and output prices

    Mistral has moved Mistral Large 4 on AI Gateway to updated weights and lowered the price of input, cached input and output tokens. According to Mistral's release announcement, the new weights improve agentic coding and defensive cybersecurity, use tokens more efficiently on coding tasks, and also improve spreadsheet creation and editing, web research, and resistance to prompt injection. Users already calling mistral/mistral-large-4 through AI Gateway need no model change to get the new weights and pricing.

  8. Vercel Labs ships agent-desktop: AI agents read desktop accessibility trees and act on refs instead of screenshots

    Vercel Labs has released agent-desktop, which lets AI agents operate desktop apps on macOS, Windows and Linux without screenshots or pixel matching. It reads an app's accessibility tree as JSON, assigns a ref to every element the agent can act on, and the agent clicks or types on a ref, then reads the UI again to verify. The tool ships as a CLI and a C library, contains no model, and leaves the observe-act-verify loop in the agent.

  9. Vercel News

    Humans&'s group-chat model Ampersand lands on AI Gateway, deciding each turn whether to speak or stay quiet

    Ampersand, a language model from Humans&, is now available free on AI Gateway through November 13, 2026. It is built for multi-person conversations such as team chats, deciding on each turn whether to speak or stay quiet, and is designed to understand individual and shared goals and help people work through disagreements. An application exposes speaking and silence as two caller-defined tools, send_message and pass, which the application executes and records; the model accepts auto and none tool choices but rejects required and named ones.

  10. Vercel News

    OpenAI's Decisions API lands on AI Gateway: swap the base URL and model ID to ask for probabilities, choices and scores

    OpenAI's Decisions API is now callable through AI Gateway at /v1/decisions, using the same request and response format as OpenAI, so existing OpenAI SDK integrations can switch by changing the base URL, credentials and model ID. Decision models answer typed questions about shared input and return structured answers rather than generated text, supporting predicate, choice and score questions for tasks such as classification, routing, triage and rubric-based scoring. The endpoint works with any decision model on AI Gateway, including Jev, Liquid d1 and Laya; OpenAI's GPT-6 Luna Decisions is reached as openai/gpt-6-luna-decisions, separate from the text-generating openai/gpt-6-luna.