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
- Novita100%Healthy24h 99.02%
- 7d
- 99.28%
- 30d
- 99.28%
- p50
- 728ms◆ (best)
- p99
- 4.02s◆ (best)
- Throughput
- 42 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.600 / $2.50◆ (best)
novita/bf16bf16 - Degraded24h 97.06%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 948ms
- p99
- 11.7s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.600 / $2.50◆ (best)
google-vertex
Measured 1m 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.