Mercury 3 from Inception now available on Vercel AI Gateway
Vercel announced that Inception's Mercury 3 model is available on AI Gateway at 50% off launch pricing. Inception reports generation speeds above 1,000 tokens per second and a 1M-token context window; Mercury 3 uses diffusion-based parallel refinement for text generation.
Why it matters
Builders running latency-sensitive workloads such as browser agents, real-time search, interactive education, or customer support can test a low-latency model with a large context window through a single gateway API, with no platform fee on inference.
Who should care
Developers building AI agents, real-time search, customer support tools, and interactive education products; teams using AI Gateway.
What you can do
Set AI_GATEWAY_API_KEY in your environment and call the model inception/mercury-3 to benchmark its latency and output quality against your current model.