Kimi K2.6
moonshotai/kimi-k2.6
Compare with Kimi K2.7 Code, Kimi K2.5, Kimi K3
CompareKimi K2.6
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.85% | 99.81% | 99.81% | 680ms | 2.83s | 33 tps | 262K | $0.950 / $4.00 | |
| Healthy | 100% | 99.44% | 99.45% | 99.45% | 399ms | 19.4s | 134 tps | 262K | $0.650 / $3.41 | |
| Healthy | 100% | 99.68% | 99.09% | 99.09% | 959ms | 10.2s | 27 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.97% | 99.91% | 99.91% | 2.00s | 15.1s | 25 tps | 262K | $0.950 / $4.00 | |
| Healthy | 100% | 99.53% | 99.04% | 99.04% | 1.07s | 6.36s | 68 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.78% | 99.80% | 99.80% | 839ms | 11.5s | 28 tps | 262K | $0.770 / $3.40 | |
| Healthy | 100% | 97.99% | 98.25% | 98.25% | 1.83s | 26.8s | 32 tps | 256K | $0.598 / $2.52 | |
| Healthy | 99.71% | 99.65% | 99.42% | 99.42% | 458ms | 7.26s | 74 tps | 262K | $0.600 / $3.41 | |
Novitanovita | Healthy | 98.65% | 99.75% | 99.66% | 99.66% | 1.49s | 7.02s | 18 tps | 262K | $0.800 / $3.40 |
| Healthy | 97.80% | 98.18% | 98.36% | 98.36% | 3.05s | 37.3s | 28 tps | 262K | $0.580 / $3.40 | |
| Degraded | 96.61% | 98.03% | 97.65% | 97.65% | 712ms | 29.9s | 74 tps | 262K | $0.587 / $2.47 | |
| Degraded | — | 95.61% | 96.46% | 96.46% | 2.67s | 10.8s | 26 tps | 262K | $0.950 / $4.00 | |
| No data | — | — | — | — | 642ms | 703ms | 22 tps | 262K | $0.950 / $4.00 | |
Cloudflarecloudflare | No data | — | 95.20% | 86.28% | 86.28% | 872ms | 5.82s | 41 tps | 262K | $0.950 / $4.00 |
| Down | — | 90.54% | 89.48% | 89.48% | 190ms | 54.2s | 22 tps | 262K | $0.700 / $3.50 | |
DigitalOceandigitalocean | No data | — | 99.86% | 99.11% | 99.11% | 1.58s | 5.04s | 47 tps | 262K | $0.950 / $4.00 |
Fireworksfireworks | No data | — | 79.31% | 96.85% | 96.85% | 614ms | 7.68s | 60 tps | 262K | $0.950 / $4.00 |
Phalaphala | No data | — | 98.70% | 98.32% | 98.32% | 1.52s | 30.0s | 20 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 | — | 96.13% | 96.29% | 96.29% | 1.08s | 6.10s | 32 tps | 256K | $0.750 / $3.50 |
- Baidu100%Healthy24h 99.85%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 680ms
- p99
- 2.83s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baidu/fp4fp4 - CoreWeave100%Healthy24h 99.44%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 399ms
- p99
- 19.4s
- Throughput
- 134 tps
- Context
- 262K
- $/Mtok
- $0.650 / $3.41
coreweave/fp4fp4 - DeepInfra100%Healthy24h 99.68%
- 7d
- 99.09%
- 30d
- 99.09%
- p50
- 959ms
- p99
- 10.2s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - Moonshot AI100%Healthy24h 99.97%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 2.00s
- p99
- 15.1s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
moonshotai/int4int4 - Parasail100%Healthy24h 99.53%
- 7d
- 99.04%
- 30d
- 99.04%
- p50
- 1.07s
- p99
- 6.36s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
parasail/int4int4 - SiliconFlow100%Healthy24h 99.78%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 839ms
- p99
- 11.5s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.770 / $3.40
siliconflow/fp8fp8 - StreamLake100%Healthy24h 97.99%
- 7d
- 98.25%
- 30d
- 98.25%
- p50
- 1.83s
- p99
- 26.8s
- Throughput
- 32 tps
- Context
- 256K
- $/Mtok
- $0.598 / $2.52
streamlake/fp8fp8 - Inceptron99.71%Healthy24h 99.65%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 458ms
- p99
- 7.26s
- Throughput
- 74 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.41
inceptron/int4int4 - Novita98.65%Healthy24h 99.75%
- 7d
- 99.66%
- 30d
- 99.66%
- p50
- 1.49s
- p99
- 7.02s
- Throughput
- 18 tps
- Context
- 262K
- $/Mtok
- $0.800 / $3.40
novita - Chutes97.80%Healthy24h 98.18%
- 7d
- 98.36%
- 30d
- 98.36%
- p50
- 3.05s
- p99
- 37.3s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.580 / $3.40
chutes/int4int4 - Decart96.61%Degraded24h 98.03%
- 7d
- 97.65%
- 30d
- 97.65%
- p50
- 712ms
- p99
- 29.9s
- Throughput
- 74 tps
- Context
- 262K
- $/Mtok
- $0.587 / $2.47
decart/fp4fp4 - Degraded24h 95.61%
- 7d
- 96.46%
- 30d
- 96.46%
- p50
- 2.67s
- p99
- 10.8s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
atlas-cloud/int4int4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- 642ms
- p99
- 703ms
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baseten/fp4fp4 - No data24h 95.20%
- 7d
- 86.28%
- 30d
- 86.28%
- p50
- 872ms
- p99
- 5.82s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
cloudflare - Down24h 90.54%
- 7d
- 89.48%
- 30d
- 89.48%
- p50
- 190ms
- p99
- 54.2s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.700 / $3.50
crusoe/bf16bf16 - No data24h 99.86%
- 7d
- 99.11%
- 30d
- 99.11%
- p50
- 1.58s
- p99
- 5.04s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
digitalocean - No data24h 79.31%
- 7d
- 96.85%
- 30d
- 96.85%
- p50
- 614ms
- p99
- 7.68s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
fireworks - No data24h 98.70%
- 7d
- 98.32%
- 30d
- 98.32%
- p50
- 1.52s
- p99
- 30.0s
- Throughput
- 20 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 96.13%
- 7d
- 96.29%
- 30d
- 96.29%
- p50
- 1.08s
- p99
- 6.10s
- Throughput
- 32 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4
Measured 2m 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.