Drama 3 now available on AI Gateway
Fish Audio's text-to-speech model Drama 3 is now available on Vercel's AI Gateway at 80% off for 30 days through Nov 12, with the model in preview under the name `fish-audio/drama-3`. Drama 3 lets dev…
Fish Audio's text-to-speech model Drama 3 is now available on Vercel's AI Gateway at 80% off for 30 days through Nov 12, with the model in preview under the name `fish-audio/drama-3`. Drama 3 lets dev…
Microsoft's MAI-Image-2.6 and MAI-Image-2.6-Flash image models are now available on Vercel's AI Gateway, callable via the AI SDK or AI CLI with one API key and no provider account. Both models support…
Google's Gemini 4 Argon is now available on Vercel's AI Gateway, the company announced, offering a 1M token context window with text, image, PDF, and video input plus tool calling. The model uses thin…
A new TanStack Start template connects an eve agent to a React frontend, using json-render to turn structured agent responses into interactive result cards, sortable tables, metrics, and step-by-step …
Meta's Muse Wonder model is now available on Vercel's AI Gateway under the model name meta/muse-wonder-1.0, giving developers access without a separate Meta account. The model targets coding, long-run…
Vercel now defaults new Pro teams to a 30-day deployment retention period, the company said, citing accelerated development from coding agents that has increased deployment frequency and stored deploy…
Microsoft's Decision-1 model is now available on Vercel's AI Gateway, letting developers ask typed questions about text and receive probabilities, choices, and scores. The model handles yes/no questio…
OpenAI's Decisions API, accessed through AI SDK's experimental_decide function and AI Gateway, lets applications return a choice, score, or probability for repeated judgment tasks such as matching fea…
XAI's Grok Imagine Video 1.5 Lite is now available on Vercel's AI Gateway, turning text prompts and images into video with native audio. The lightweight model generates clips from 1 to 15 seconds in 4…
StepFun's flagship model Step 5 Preview is now available on Vercel's AI Gateway under the model name stepfun/step-5-preview, supporting text and image input with a 1M-token context window. Vercel said…
Liquid AI's d1 decision model is now available on Vercel's AI Gateway, where it evaluates shared state against typed questions for classification, routing, and scoring and returns structured answers w…
OpenAI's Decisions API can evaluate a GitHub pull request's diff against specific review questions, such as which review track a change belongs in and whether existing callers need migration guidance,…
OpenAI's Decisions API is now available on Vercel's AI Gateway through an OpenAI-compatible /v1/decisions endpoint, letting developers run decision models that return probabilities, choices and scores…
Vercel added the stealth reasoning model Glyph Cluster to AI Gateway, free to use during the stealth period for teams on Pro and Enterprise plans with purchased AI Gateway credits. Glyph Cluster handl…
Anthropic's Claude Haiku 5.5 is now available on Vercel's AI Gateway under the model name anthropic/claude-haiku-5.5, positioned as a direct upgrade to Claude Haiku 4.5 for high-volume, cost-sensitive…
Vercel's AI Gateway added confidence-based decision fallbacks in beta, letting developers escalate a decision request to a fallback model when the primary model's answer trips a confidence condition t…
Mistral Large 4, an open-weight, natively multimodal model combining reasoning with text and image understanding, is now available on Vercel's AI Gateway, the company said. Developers can access the m…
Google's Nano Banana 2.1 image generation and editing model is now available on Vercel's AI Gateway under the model ID google/gemini-nano-banana-2.1, Vercel announced. The release improves on earlier …
OpenInstinct released Eve, an open-source, self-hostable personal iMessage assistant that can operate a browser to book movie tickets, handle groceries and complete other chores while keeping password…
Perplexity released the Decisions API, which evaluates supplied content and returns typed predictions with probabilities using its pplx-decider-v1-27b model that accepts text and images. The API separ…