Mercury 3 from @_inception_ai is live on AI Gateway at a 50% discount.
A high-throughput diffusion model with a 1M-token context window and support for tool calling and structured outputs.
πππππππππ/πππππππ’-πΉ
vercel.com/changelog/mercβ¦
A high-throughput diffusion model with a 1M-token context window and support for tool calling and structured outputs.
πππππππππ/πππππππ’-πΉ
vercel.com/changelog/mercβ¦
Oct 19, 2026 Β· 6:21 PM UTC
6
5
109
35,225
@vercel_dev @_inception_ai 50% off launch pricing is a smart move. I have been running my agents through AI Gateway for months and the latency difference on diffusion models is honestly the whole selling point for me.
0
0
3
621
@vercel_dev @_inception_ai a diffusion model with tool calling is new to me. does it still stream the output, or does the whole answer land at once?
1
0
2
728
70% of customer interactions will soon be automated - but most voice AI solutions still struggle with latency, rigid scripts, and unreliable call experiences. We're changing that with ππ πππππΌπΊπ²πΏ π¦π²πΏππΆπ°π² ππ΄π²π»ππ.
20
30
229
6,288,535