Pareto Inference models

Get API key Read the docs

Route requests to Pareto Inference through Vercel AI Gateway. Compare the models Pareto Inference serves, with unified billing and automatic failover across providers.

Model	Context	Input	Output	Latency	Throughput	Cache	Search	Capabilities	ZDR	No Training	Regional Inference	Free AI Gateway Credit	Released

deepseek/deepseek-v4.1-flash-1017

$0.08/M

$0.30/M

1.9 s

329 tps

Read$0.0015/M

—

10/17/2026