Kimi K2 Thinking
moonshotai/kimi-k2-thinking
Compare with Kimi K2 0711, Kimi K2 0905, Kimi K2.5
CompareKimi K2 Thinking
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex | Healthy | 99.30% | 99.77% | 366ms | 2.01s | 91 tps | 262K | $0.600 / $2.50 |
Novitanovita/bf16bf16 | Healthy | 98.84% | 99.28% | 1.03s | 8.96s | 36 tps | 262K | $0.600 / $2.50 |
- Google99.30%Healthy24h 99.77%
- p50
- 366ms
- p99
- 2.01s
- Throughput
- 91 tps
- Context
- 262K
- $/Mtok
- $0.600 / $2.50
google-vertex - Novita98.84%Healthy24h 99.28%
- p50
- 1.03s
- p99
- 8.96s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.600 / $2.50
novita/bf16bf16
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.