Inception Mercury 2 is live on AI Gateway

Mercury 2 from Inception is now available on Vercel AI Gateway.

Mercury 2 from Inception is now available on AI Gateway. Mercury 2 delivers reasoning-grade quality at real-time latency, making it ideal for agentic loops, coding assistants, voice interfaces, and RAG pipelines where compounding latency is the bottleneck.

To use Mercury 2, set model to inception/mercury-2 in the AI SDK.

1
import { streamText } from 'ai';
2

3
const result = streamText({
4
  model: 'inception/mercury-2',
5
  prompt:
6
    `For each incoming support ticket, classify urgency,
7
     retrieve relevant docs, draft a response, and escalate
8
     if unresolved.`,
9
});

AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in observability, Bring Your Own Key support, and intelligent provider routing with automatic retries.

Learn more about AI Gateway, view the AI Gateway model leaderboard or try it in our model playground.