Anthropic AI Gateway Benchmark
Request Latency
Cold E2E
597ms
Median
Warm TTFT
484ms
Median
Tokens/sec
58
Median
DNS
0.9ms
Median
TCP
19.9ms
Median
TLS
22.1ms
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.
DNS0.9ms
TCP19.9ms
TLS22.1ms
To First Byte511.0ms
First Byte → Token0.2ms
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.