Kimi K2.6
moonshotai/kimi-k2.6
Compare with Kimi K2.7 Code, Kimi K2.5, Kimi K3
CompareKimi K2.6
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.82% | 99.81% | 99.81% | 940ms | 4.91s | 33 tps | 262K | $0.950 / $4.00 | |
| Healthy | 100% | 99.69% | 99.08% | 99.08% | 822ms | 8.70s | 29 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.96% | 99.90% | 99.90% | 2.15s | 16.8s | 24 tps | 262K | $0.950 / $4.00 | |
| Healthy | 100% | 99.52% | 99.02% | 99.02% | 1.18s | 10.6s | 60 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.78% | 99.80% | 99.80% | 886ms | 10.3s | 31 tps | 262K | $0.770 / $3.40 | |
| Healthy | 99.52% | 99.65% | 99.41% | 99.41% | 533ms | 6.01s | 71 tps | 262K | $0.600 / $3.41 | |
Novitanovita | Healthy | 98.90% | 99.71% | 99.66% | 99.66% | 1.48s | 9.00s | 20 tps | 262K | $0.800 / $3.40 |
| Healthy | 98.53% | 99.44% | 99.45% | 99.45% | 703ms | 13.1s | 96 tps | 262K | $0.650 / $3.41 | |
| Healthy | 97.40% | 97.87% | 98.28% | 98.28% | 2.76s | 20.2s | 31 tps | 256K | $0.598 / $2.52 | |
| Healthy | 97.38% | 98.16% | 98.37% | 98.37% | 1.68s | 27.5s | 28 tps | 262K | $0.580 / $3.40 | |
| Healthy | 97.14% | 98.12% | 97.64% | 97.64% | 592ms | 21.8s | 82 tps | 262K | $0.587 / $2.47 | |
| Down | 28.57% | 90.89% | 89.84% | 89.84% | 262ms | 23.3s | 27 tps | 262K | $0.700 / $3.50 | |
| Degraded | — | 94.93% | 96.57% | 96.57% | 2.74s | 23.0s | 25 tps | 262K | $0.950 / $4.00 | |
| No data | — | — | — | — | 658ms | 22.5s | 31 tps | 262K | $0.950 / $4.00 | |
Cloudflarecloudflare | No data | — | 93.70% | 86.02% | 86.02% | 600ms | 4.26s | 48 tps | 262K | $0.950 / $4.00 |
DigitalOceandigitalocean | No data | — | 99.86% | 99.16% | 99.16% | 1.04s | 7.00s | 42 tps | 262K | $0.950 / $4.00 |
Fireworksfireworks | No data | — | 79.55% | 96.85% | 96.85% | 632ms | 7.43s | 61 tps | 262K | $0.950 / $4.00 |
Phalaphala | No data | — | 98.73% | 98.32% | 98.32% | 1.86s | 16.2s | 17 tps | 262K | $1.09 / $4.60 |
| No data | — | — | 99.88% | 99.88% | — | — | — | 262K | $1.00 / $4.00 | |
Togethertogether | No data | — | — | 97.92% | 97.92% | — | — | — | 262K | $1.20 / $4.50 |
| No data | — | 96.21% | 96.23% | 96.23% | 1.10s | 11.1s | 26 tps | 256K | $0.750 / $3.50 |
- Baidu100%Healthy24h 99.82%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 940ms
- p99
- 4.91s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baidu/fp4fp4 - DeepInfra100%Healthy24h 99.69%
- 7d
- 99.08%
- 30d
- 99.08%
- p50
- 822ms
- p99
- 8.70s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - Moonshot AI100%Healthy24h 99.96%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 2.15s
- p99
- 16.8s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
moonshotai/int4int4 - Parasail100%Healthy24h 99.52%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 1.18s
- p99
- 10.6s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
parasail/int4int4 - SiliconFlow100%Healthy24h 99.78%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 886ms
- p99
- 10.3s
- Throughput
- 31 tps
- Context
- 262K
- $/Mtok
- $0.770 / $3.40
siliconflow/fp8fp8 - Inceptron99.52%Healthy24h 99.65%
- 7d
- 99.41%
- 30d
- 99.41%
- p50
- 533ms
- p99
- 6.01s
- Throughput
- 71 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.41
inceptron/int4int4 - Novita98.90%Healthy24h 99.71%
- 7d
- 99.66%
- 30d
- 99.66%
- p50
- 1.48s
- p99
- 9.00s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.800 / $3.40
novita - CoreWeave98.53%Healthy24h 99.44%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 703ms
- p99
- 13.1s
- Throughput
- 96 tps
- Context
- 262K
- $/Mtok
- $0.650 / $3.41
coreweave/fp4fp4 - StreamLake97.40%Healthy24h 97.87%
- 7d
- 98.28%
- 30d
- 98.28%
- p50
- 2.76s
- p99
- 20.2s
- Throughput
- 31 tps
- Context
- 256K
- $/Mtok
- $0.598 / $2.52
streamlake/fp8fp8 - Chutes97.38%Healthy24h 98.16%
- 7d
- 98.37%
- 30d
- 98.37%
- p50
- 1.68s
- p99
- 27.5s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.580 / $3.40
chutes/int4int4 - Decart97.14%Healthy24h 98.12%
- 7d
- 97.64%
- 30d
- 97.64%
- p50
- 592ms
- p99
- 21.8s
- Throughput
- 82 tps
- Context
- 262K
- $/Mtok
- $0.587 / $2.47
decart/fp4fp4 - Crusoe28.57%Down24h 90.89%
- 7d
- 89.84%
- 30d
- 89.84%
- p50
- 262ms
- p99
- 23.3s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.700 / $3.50
crusoe/bf16bf16 - Degraded24h 94.93%
- 7d
- 96.57%
- 30d
- 96.57%
- p50
- 2.74s
- p99
- 23.0s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
atlas-cloud/int4int4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- 658ms
- p99
- 22.5s
- Throughput
- 31 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baseten/fp4fp4 - No data24h 93.70%
- 7d
- 86.02%
- 30d
- 86.02%
- p50
- 600ms
- p99
- 4.26s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
cloudflare - No data24h 99.86%
- 7d
- 99.16%
- 30d
- 99.16%
- p50
- 1.04s
- p99
- 7.00s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
digitalocean - No data24h 79.55%
- 7d
- 96.85%
- 30d
- 96.85%
- p50
- 632ms
- p99
- 7.43s
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
fireworks - No data24h 98.73%
- 7d
- 98.32%
- 30d
- 98.32%
- p50
- 1.86s
- p99
- 16.2s
- Throughput
- 17 tps
- Context
- 262K
- $/Mtok
- $1.09 / $4.60
phala - No data24h —
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $1.00 / $4.00
sail-research/int4int4 - No data24h —
- 7d
- 97.92%
- 30d
- 97.92%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $1.20 / $4.50
together - No data24h 96.21%
- 7d
- 96.23%
- 30d
- 96.23%
- p50
- 1.10s
- p99
- 11.1s
- Throughput
- 26 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Kimi K2.6DigitalOceandigitalocean$0.760 / $3.20 → $0.950 / $4.002026-08-21 03:30 UTC
- Kimi K2.6Decartdecart/fp4$0.549 / $2.31 → $0.587 / $2.472026-08-21 01:20 UTC
- Kimi K2.6Baidubaidu/fp4$0.541 / $2.28 → $0.950 / $4.002026-08-20 23:40 UTC
- Kimi K2.6Baidubaidu/fp4$0.560 / $2.36 → $0.541 / $2.282026-08-20 19:45 UTC
- Kimi K2.6Decartdecart/fp4$0.568 / $2.39 → $0.549 / $2.312026-08-20 17:56 UTC
- Kimi K2.6Baidubaidu/fp4$0.580 / $2.44 → $0.560 / $2.362026-08-20 16:51 UTC
- Kimi K2.6Decartdecart/fp4$0.587 / $2.47 → $0.568 / $2.392026-08-20 16:01 UTC
- Kimi K2.6Baidubaidu/fp4$0.941 / $3.96 → $0.580 / $2.442026-08-20 13:45 UTC
- Kimi K2.6Baidubaidu/fp4$0.950 / $4.00 → $0.941 / $3.962026-08-20 12:50 UTC
- Kimi K2.6Decartdecart/fp4$0.549 / $2.31 → $0.587 / $2.472026-08-20 00:50 UTC
- Kimi K2.6Baidubaidu/fp4$0.541 / $2.28 → $0.950 / $4.002026-08-19 23:40 UTC
- Kimi K2.6Baidubaidu/fp4$0.560 / $2.36 → $0.541 / $2.282026-08-19 18:50 UTC
- Kimi K2.6Decartdecart/fp4$0.568 / $3.33 → $0.549 / $2.312026-08-19 17:55 UTC
- Kimi K2.6Baidubaidu/fp4$0.646 / $2.72 → $0.560 / $2.362026-08-19 15:45 UTC
- Kimi K2.6Baidubaidu/fp4$0.950 / $4.00 → $0.646 / $2.722026-08-19 14:50 UTC
- Kimi K2.6Baidubaidu/fp4$0.941 / $3.96 → $0.950 / $4.002026-08-19 13:50 UTC
- Kimi K2.6Baidubaidu/fp4$0.950 / $4.00 → $0.941 / $3.962026-08-19 12:40 UTC
History
8 endpoints reporting no data are omitted from the charts.
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.