Kimi K2 Thinking: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Google100%◆ (best)Healthy24h 97.07%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 406ms◆ (best)
- p99
- 2.53s◆ (best)
- Throughput
- 139 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.600 / $2.50◆ (best)
google-vertex - Novita98.68%Healthy24h 99.07%
- 7d
- 99.29%
- 30d
- 99.29%
- p50
- 1.42s
- p99
- 11.6s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.600 / $2.50◆ (best)
novita/bf16bf16
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.