Kimi K2.6
moonshotai/kimi-k2.6
Compare with Kimi K2.7 Code, Kimi K2.5, Kimi K3
CompareKimi K2.6
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.81% | 99.81% | 99.81% | 919ms | 4.10s | 30 tps | 262K | $0.950 / $4.00 | |
Cloudflarecloudflare | Healthy | 100% | 92.31% | 85.75% | 85.75% | 574ms | 14.9s | 51 tps | 262K | $0.950 / $4.00 |
| Healthy | 100% | 99.46% | 99.46% | 99.46% | 492ms | 15.5s | 114 tps | 262K | $0.650 / $3.41 | |
| Degraded | 100% | 90.43% | 89.80% | 89.80% | 393ms | 30.8s | 21 tps | 262K | $0.700 / $3.50 | |
| Healthy | 100% | 99.70% | 99.07% | 99.07% | 815ms | 3.97s | 34 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.66% | 99.40% | 99.40% | 551ms | 5.00s | 63 tps | 262K | $0.600 / $3.41 | |
| Healthy | 100% | 99.94% | 99.90% | 99.90% | 1.87s | 13.8s | 24 tps | 262K | $0.950 / $4.00 | |
Novitanovita | Healthy | 100% | 99.68% | 99.65% | 99.65% | 1.50s | 8.91s | 19 tps | 262K | $0.800 / $3.40 |
| Healthy | 100% | 99.52% | 99.00% | 99.00% | 1.23s | 6.81s | 79 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 96.29% | 96.17% | 96.17% | 1.07s | 4.52s | 35 tps | 256K | $0.750 / $3.50 | |
| Healthy | 99.58% | 97.80% | 98.29% | 98.29% | 1.22s | 15.4s | 22 tps | 256K | $0.598 / $2.52 | |
| Healthy | 99.46% | 99.76% | 99.81% | 99.81% | 758ms | 9.46s | 29 tps | 262K | $0.770 / $3.40 | |
| Healthy | 98.28% | 98.18% | 98.37% | 98.37% | 2.17s | 22.7s | 27 tps | 262K | $0.580 / $3.40 | |
| Healthy | 97.64% | 98.16% | 97.71% | 97.71% | 398ms | 7.39s | 73 tps | 262K | $0.587 / $2.47 | |
DigitalOceandigitalocean | Healthy | 97.06% | 99.87% | 99.20% | 99.20% | 1.11s | 8.77s | 42 tps | 262K | $0.950 / $4.00 |
| Degraded | — | 94.92% | 96.86% | 96.86% | 3.17s | 41.1s | 27 tps | 262K | $0.950 / $4.00 | |
| No data | — | — | — | — | 637ms | 699ms | 23 tps | 262K | $0.950 / $4.00 | |
Fireworksfireworks | No data | — | 79.57% | 96.85% | 96.85% | 531ms | 6.95s | 68 tps | 262K | $0.950 / $4.00 |
Phalaphala | No data | — | 98.70% | 98.36% | 98.36% | 1.66s | 8.21s | 18 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 |
- Baidu100%Healthy24h 99.81%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 919ms
- p99
- 4.10s
- Throughput
- 30 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baidu/fp4fp4 - Cloudflare100%Healthy24h 92.31%
- 7d
- 85.75%
- 30d
- 85.75%
- p50
- 574ms
- p99
- 14.9s
- Throughput
- 51 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
cloudflare - CoreWeave100%Healthy24h 99.46%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 492ms
- p99
- 15.5s
- Throughput
- 114 tps
- Context
- 262K
- $/Mtok
- $0.650 / $3.41
coreweave/fp4fp4 - Crusoe100%Degraded24h 90.43%
- 7d
- 89.80%
- 30d
- 89.80%
- p50
- 393ms
- p99
- 30.8s
- Throughput
- 21 tps
- Context
- 262K
- $/Mtok
- $0.700 / $3.50
crusoe/bf16bf16 - DeepInfra100%Healthy24h 99.70%
- 7d
- 99.07%
- 30d
- 99.07%
- p50
- 815ms
- p99
- 3.97s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - Inceptron100%Healthy24h 99.66%
- 7d
- 99.40%
- 30d
- 99.40%
- p50
- 551ms
- p99
- 5.00s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.41
inceptron/int4int4 - Moonshot AI100%Healthy24h 99.94%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 1.87s
- p99
- 13.8s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
moonshotai/int4int4 - Novita100%Healthy24h 99.68%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 1.50s
- p99
- 8.91s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.800 / $3.40
novita - Parasail100%Healthy24h 99.52%
- 7d
- 99.00%
- 30d
- 99.00%
- p50
- 1.23s
- p99
- 6.81s
- Throughput
- 79 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
parasail/int4int4 - Venice100%Healthy24h 96.29%
- 7d
- 96.17%
- 30d
- 96.17%
- p50
- 1.07s
- p99
- 4.52s
- Throughput
- 35 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - StreamLake99.58%Healthy24h 97.80%
- 7d
- 98.29%
- 30d
- 98.29%
- p50
- 1.22s
- p99
- 15.4s
- Throughput
- 22 tps
- Context
- 256K
- $/Mtok
- $0.598 / $2.52
streamlake/fp8fp8 - SiliconFlow99.46%Healthy24h 99.76%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 758ms
- p99
- 9.46s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.770 / $3.40
siliconflow/fp8fp8 - Chutes98.28%Healthy24h 98.18%
- 7d
- 98.37%
- 30d
- 98.37%
- p50
- 2.17s
- p99
- 22.7s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.580 / $3.40
chutes/int4int4 - Decart97.64%Healthy24h 98.16%
- 7d
- 97.71%
- 30d
- 97.71%
- p50
- 398ms
- p99
- 7.39s
- Throughput
- 73 tps
- Context
- 262K
- $/Mtok
- $0.587 / $2.47
decart/fp4fp4 - DigitalOcean97.06%Healthy24h 99.87%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 1.11s
- p99
- 8.77s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
digitalocean - Degraded24h 94.92%
- 7d
- 96.86%
- 30d
- 96.86%
- p50
- 3.17s
- p99
- 41.1s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
atlas-cloud/int4int4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- 637ms
- p99
- 699ms
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baseten/fp4fp4 - No data24h 79.57%
- 7d
- 96.85%
- 30d
- 96.85%
- p50
- 531ms
- p99
- 6.95s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
fireworks - No data24h 98.70%
- 7d
- 98.36%
- 30d
- 98.36%
- p50
- 1.66s
- p99
- 8.21s
- Throughput
- 18 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
Measured 5m 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
5 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.