Anthropic AI Gateway Benchmark
Request Latency
Cold E2E
1088ms
Median
Warm TTFT
736ms
Median
Tokens/sec
44
Median
DNS
0.8ms
Median
TCP
84.0ms
Median
TLS
85.6ms
Median
Cold Connection Breakdown
Where a fresh request's time goes: DNS lookup, TCP connect, TLS handshake, then time to first response byte, then first byte to first streamed token.
DNS0.8ms
TCP84.0ms
TLS85.6ms
To First Byte732.4ms
First Byte → Token3.7ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Become a partner
Want your logo featured across our benchmarks? Become a ComputeSDK benchmark partner.