Skip to content
GitHub

Product

Benchmarks Partners

Resources

Docs Blog

Kimi (Direct) Kimi AI Gateway Benchmarks

Kimi (Direct)
Kimi AI Gateway Benchmarks

Last benchmarked August 21, 2026

No-gateway control — a direct call to Kimi's API, used to measure how much latency each gateway adds.

Request Latency

Baseline
95% success

No gateway involved — a direct call to Anthropic's API, used as the no-gateway control every other provider is compared against.

Cold E2E
1258ms
Median
Warm TTFT
2240ms
Median
Tokens/sec
35
Median
DNS
25.0ms
Median
TCP
1.0ms
Median
TLS
6.2ms
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.

DNS25.0ms
TCP1.0ms
TLS6.2ms
To First Byte1147.1ms
First Byte → Token0.1ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

PartnersLatitude