Kimi K2.6
moonshotai/kimi-k2.6
Compare with Kimi K2.7 Code, Kimi K3, Kimi K2.5
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | Healthy | 100% | 99.97% | 760ms | 7.93s | 45 tps | 262K | $0.950 / $4.00 |
Crusoecrusoe/bf16bf16 | Down | 100% | 98.43% | 903ms | 32.6s | 19 tps | 262K | $0.700 / $3.50 |
DigitalOceandigitalocean | Healthy | 100% | 99.76% | 1.20s | 7.69s | 29 tps | 262K | $0.760 / $3.20 |
Inceptroninceptron/int4int4 | Healthy | 100% | 99.64% | 614ms | 7.72s | 39 tps | 262K | $0.600 / $3.41 |
Moonshot AImoonshotai/int4int4 | Healthy | 100% | 99.95% | 1.85s | 16.7s | 28 tps | 262K | $0.950 / $4.00 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 99.93% | 900ms | 27.6s | 42 tps | 262K | $0.770 / $3.40 |
Togethertogether | Degraded | 100% | 90.59% | 490ms | 14.5s | 66 tps | 262K | $1.20 / $4.50 |
Venicevenice/int4int4 | Healthy | 100% | 78.44% | 1.15s | 6.64s | 19 tps | 256K | $0.750 / $3.50 |
Baidubaidu/fp4fp4 | Healthy | 99.49% | 99.90% | 589ms | 3.63s | 25 tps | 262K | $0.950 / $4.00 |
Novitanovita | Healthy | 99.49% | 99.73% | 1.77s | 26.4s | 37 tps | 262K | $0.800 / $3.40 |
CoreWeavecoreweave/fp4fp4 | Healthy | 99.29% | 99.14% | 733ms | 13.0s | 106 tps | 262K | $0.650 / $3.41 |
StreamLakestreamlake/fp8fp8 | Healthy | 99.25% | 98.40% | 2.11s | 22.9s | 31 tps | 256K | $0.598 / $2.52 |
Chuteschutes/int4int4 | Healthy | 98.01% | 98.51% | 2.90s | 29.5s | 22 tps | 262K | $0.580 / $3.40 |
Decartdecart/fp4fp4 | Degraded | 90.84% | 97.40% | 842ms | 49.9s | 47 tps | 262K | $0.568 / $3.33 |
AtlasCloudatlas-cloud/int4int4 | No data | — | 97.62% | 1.38s | 10.4s | 27 tps | 262K | $0.950 / $4.00 |
BaseTenbaseten/fp4fp4 | No data | — | — | 892ms | 3.72s | 59 tps | 262K | $0.950 / $4.00 |
DeepInfradeepinfra/fp4fp4 | No data | — | 98.01% | 846ms | 5.01s | 20 tps | 262K | $0.750 / $3.50 |
Fireworksfireworks | No data | — | 0.00% | 472ms | 6.06s | 76 tps | 262K | $0.950 / $4.00 |
Parasailparasail/int4int4 | No data | — | 99.35% | — | — | — | 262K | $0.750 / $3.50 |
Phalaphala | No data | — | 99.62% | 1.50s | 10.5s | 17 tps | 262K | $1.09 / $4.60 |
Sail Researchsail-research/int4int4 | No data | — | 99.86% | 915ms | 3.20s | 32 tps | 262K | $1.00 / $4.00 |
- Cloudflare100%Healthy24h 99.97%
- p50
- 760ms
- p99
- 7.93s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
cloudflare - Crusoe100%Down24h 98.43%
- p50
- 903ms
- p99
- 32.6s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.700 / $3.50
crusoe/bf16bf16 - DigitalOcean100%Healthy24h 99.76%
- p50
- 1.20s
- p99
- 7.69s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.760 / $3.20
digitalocean - Inceptron100%Healthy24h 99.64%
- p50
- 614ms
- p99
- 7.72s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.41
inceptron/int4int4 - Moonshot AI100%Healthy24h 99.95%
- p50
- 1.85s
- p99
- 16.7s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
moonshotai/int4int4 - SiliconFlow100%Healthy24h 99.93%
- p50
- 900ms
- p99
- 27.6s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.770 / $3.40
siliconflow/fp8fp8 - Together100%Degraded24h 90.59%
- p50
- 490ms
- p99
- 14.5s
- Throughput
- 66 tps
- Context
- 262K
- $/Mtok
- $1.20 / $4.50
together - Venice100%Healthy24h 78.44%
- p50
- 1.15s
- p99
- 6.64s
- Throughput
- 19 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - Baidu99.49%Healthy24h 99.90%
- p50
- 589ms
- p99
- 3.63s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baidu/fp4fp4 - Novita99.49%Healthy24h 99.73%
- p50
- 1.77s
- p99
- 26.4s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.800 / $3.40
novita - CoreWeave99.29%Healthy24h 99.14%
- p50
- 733ms
- p99
- 13.0s
- Throughput
- 106 tps
- Context
- 262K
- $/Mtok
- $0.650 / $3.41
coreweave/fp4fp4 - StreamLake99.25%Healthy24h 98.40%
- p50
- 2.11s
- p99
- 22.9s
- Throughput
- 31 tps
- Context
- 256K
- $/Mtok
- $0.598 / $2.52
streamlake/fp8fp8 - Chutes98.01%Healthy24h 98.51%
- p50
- 2.90s
- p99
- 29.5s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.580 / $3.40
chutes/int4int4 - Decart90.84%Degraded24h 97.40%
- p50
- 842ms
- p99
- 49.9s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.568 / $3.33
decart/fp4fp4 - AtlasCloud—No data24h 97.62%
- p50
- 1.38s
- p99
- 10.4s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
atlas-cloud/int4int4 - BaseTen—No data24h —
- p50
- 892ms
- p99
- 3.72s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
baseten/fp4fp4 - DeepInfra—No data24h 98.01%
- p50
- 846ms
- p99
- 5.01s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - Fireworks—No data24h 0.00%
- p50
- 472ms
- p99
- 6.06s
- Throughput
- 76 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
fireworks - Parasail—No data24h 99.35%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
parasail/int4int4 - Phala—No data24h 99.62%
- p50
- 1.50s
- p99
- 10.5s
- Throughput
- 17 tps
- Context
- 262K
- $/Mtok
- $1.09 / $4.60
phala - Sail Research—No data24h 99.86%
- p50
- 915ms
- p99
- 3.20s
- Throughput
- 32 tps
- Context
- 262K
- $/Mtok
- $1.00 / $4.00
sail-research/int4int4
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
7 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.