#AI Gateway
13 related articles
Mistral Large 4 Updates Weights and Cuts Prices, AI Gateway Users Upgrade Seamlessly
Mistral Large 4 updates weights and lowers input, cached input, and output token prices on AI Gateway, enhancing agentic coding and defensive cybersecurity. Existing model IDs point to the new version automatically—seamless upgrade with no code changes.
AI Gateway Introduces Virtual Models: Switch Models Without Changing Code
Vercel AI Gateway launches Virtual Models, abstracting model strings and configuration into reusable IDs so model switching needs no code changes or redeployment, with centralized governance of fallback, Zero Data Retention, and permission control.
AI Gateway Launches Virtual Models: Centralized Model Configuration Without Redeployment
AI Gateway launches Virtual Models, using custom model IDs to centrally manage model selection and parameters, with agent setting injection, provider routing, ZDR compliance, and cost attribution—no redeployment needed.
Particle-1 Lands on AI Gateway: A Token-Efficient Model Built for Software Engineering
Particle AI's Particle-1 model launches on Vercel AI Gateway, post-trained on DeepSeek V4.1 Flash to complete software engineering tasks with fewer tokens, featuring a 1M-token context for debugging, code change planning, and multi-step problem breakdown.
ElevenLabs Lands on Vercel AI Gateway: 14 Voice Models in One Place
Vercel and ElevenLabs bring 14 voice models to AI Gateway, covering speech-to-text, streaming TTS, real-time voice agents, music and sound effects, and multi-speaker dialogue—all with one API key, unified usage tracking, and no markup.
GPT-6.1 Terra Launches on AI Gateway: A New Choice for Visual Reasoning and Computer Operation
GPT-6.1 Terra is now available on AI Gateway, focused on visual reasoning, computer operation, and writing, with a 1M+ token context window, structured outputs, and prompt caching for high-throughput document and desktop automation.
Baseten Mammoth-1 and Elephant-1 Decision Models Launch Free on AI Gateway for a Limited Time
Baseten's decision models Mammoth-1 (27B) and Elephant-1 (9B) are now free on AI Gateway for a limited time, supporting text classification, request routing, and content scoring with 16k context. Free calls until October 27.
Mercury 3 Launches on AI Gateway: Diffusion-Based Text Generation Exceeds 1,000 Tokens/s
Inception's Mercury 3 launches on Vercel AI Gateway, using diffusion-based parallel refinement to generate text at over 1,000 tokens/s with a 1M token context, 50% off at launch, suited for browser agents and real-time search.
MiniMax M3.1 Flash Launches Free on AI Gateway: A Multimodal Model with 1M Context
MiniMax M3.1 Flash is free on Vercel AI Gateway through October 20. The open-weight multimodal model supports a 1M-token context and strengthens coding, agentic, and computer use capabilities.
Elorian Glimpse Visual Reasoning Model Lands on AI Gateway
Elorian's visual reasoning model Glimpse joins AI Gateway, supporting image and video inputs with cross-frame object tracking and visual evidence backtracking for chart analysis, video description, visual counting, and robot data annotation. This article covers its capabilities, AI SDK integration code, and frame rate configuration tips.
Fish Audio Drama 3 Lands on AI Gateway: Direct Voice Performances with Natural Language
Fish Audio's text-to-speech model Drama 3 launches on AI Gateway, enabling natural language direction of voice emotion and pacing, with whisper and emphasis tags, multilingual instructions, and multi-character dialogue, plus 80% off for 30 days.
Jev Sets AI Gateway's Fastest Adoption Record: Reached 13% of Teams on Day One
AI model Jev sets AI Gateway's fastest-ever adoption record, reaching ~13% of teams on day one — 2x GPT-5.6 and 6x Fable 5.1. Here's what the data means.
