Kimi K2.6

moonshotai/kimi-k2.6

Compare with Kimi K2.7 Code, Kimi K2.5, Kimi K3

CompareKimi K2.6

Provider	State	Uptime 5m	24h	p50 latency	p99	Throughput	Context	$/Mtok
AtlasCloudatlas-cloud/int4int4	Healthy	100%	97.79%	1.09s	6.66s	21 tps	262K	$0.950 / $4.00
Baidubaidu/fp4fp4	Healthy	100%	99.88%	1.04s	5.15s	41 tps	262K	$0.560 / $2.36
Chuteschutes/int4int4	Healthy	100%	98.60%	1.50s	7.71s	23 tps	262K	$0.580 / $3.40
Cloudflarecloudflare	Healthy	100%	99.97%	648ms	5.19s	37 tps	262K	$0.950 / $4.00
Crusoecrusoe/bf16bf16	Healthy	100%	98.29%	421ms	16.0s	31 tps	262K	$0.700 / $3.50
DeepInfradeepinfra/fp4fp4	Healthy	100%	98.02%	822ms	5.96s	20 tps	262K	$0.750 / $3.50
DigitalOceandigitalocean	Healthy	100%	99.69%	586ms	4.42s	31 tps	262K	$0.760 / $3.20
Inceptroninceptron/int4int4	Healthy	100%	99.61%	512ms	5.25s	69 tps	262K	$0.600 / $3.41
Moonshot AImoonshotai/int4int4	Healthy	100%	99.97%	1.33s	10.1s	32 tps	262K	$0.950 / $4.00
Novitanovita	Healthy	100%	99.73%	2.37s	10.3s	29 tps	262K	$0.800 / $3.40
Parasailparasail/int4int4	Healthy	100%	99.32%	580ms	5.97s	61 tps	262K	$0.750 / $3.50
Sail Researchsail-research/int4int4	Healthy	100%	99.91%	873ms	4.94s	22 tps	262K	$1.00 / $4.00
SiliconFlowsiliconflow/fp8fp8	Healthy	100%	99.92%	1.06s	97.0s	24 tps	262K	$0.770 / $3.40
StreamLakestreamlake/fp8fp8	Healthy	100%	98.36%	1.41s	10.7s	26 tps	256K	$0.598 / $2.52
Togethertogether	Healthy	100%	91.17%	370ms	6.14s	115 tps	262K	$1.20 / $4.50
Venicevenice/int4int4	Healthy	100%	80.65%	1.07s	7.22s	18 tps	256K	$0.750 / $3.50
Decartdecart/fp4fp4	Healthy	99.80%	97.70%	539ms	7.07s	74 tps	262K	$0.568 / $3.33
CoreWeavecoreweave/fp4fp4	Healthy	99.39%	99.14%	379ms	5.31s	144 tps	262K	$0.650 / $3.41
Phalaphala	Healthy	98.08%	99.55%	1.42s	10.6s	20 tps	262K	$1.09 / $4.60
BaseTenbaseten/fp4fp4	No data	—	—	3.76s	5.70s	67 tps	262K	$0.950 / $4.00
Fireworksfireworks	No data	—	0.00%	494ms	6.25s	73 tps	262K	$0.950 / $4.00

AtlasCloud100%
Healthy24h 97.79%
p50
1.09s
p99
6.66s
Throughput
21 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
Baidu100%
Healthy24h 99.88%
p50
1.04s
p99
5.15s
Throughput
41 tps
Context
262K
$/Mtok
$0.560 / $2.36
baidu/fp4fp4
Chutes100%
Healthy24h 98.60%
p50
1.50s
p99
7.71s
Throughput
23 tps
Context
262K
$/Mtok
$0.580 / $3.40
chutes/int4int4
Cloudflare100%
Healthy24h 99.97%
p50
648ms
p99
5.19s
Throughput
37 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
Crusoe100%
Healthy24h 98.29%
p50
421ms
p99
16.0s
Throughput
31 tps
Context
262K
$/Mtok
$0.700 / $3.50
crusoe/bf16bf16
DeepInfra100%
Healthy24h 98.02%
p50
822ms
p99
5.96s
Throughput
20 tps
Context
262K
$/Mtok
$0.750 / $3.50
deepinfra/fp4fp4
DigitalOcean100%
Healthy24h 99.69%
p50
586ms
p99
4.42s
Throughput
31 tps
Context
262K
$/Mtok
$0.760 / $3.20
digitalocean
Inceptron100%
Healthy24h 99.61%
p50
512ms
p99
5.25s
Throughput
69 tps
Context
262K
$/Mtok
$0.600 / $3.41
inceptron/int4int4
Moonshot AI100%
Healthy24h 99.97%
p50
1.33s
p99
10.1s
Throughput
32 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
Novita100%
Healthy24h 99.73%
p50
2.37s
p99
10.3s
Throughput
29 tps
Context
262K
$/Mtok
$0.800 / $3.40
novita
Parasail100%
Healthy24h 99.32%
p50
580ms
p99
5.97s
Throughput
61 tps
Context
262K
$/Mtok
$0.750 / $3.50
parasail/int4int4
Sail Research100%
Healthy24h 99.91%
p50
873ms
p99
4.94s
Throughput
22 tps
Context
262K
$/Mtok
$1.00 / $4.00
sail-research/int4int4
SiliconFlow100%
Healthy24h 99.92%
p50
1.06s
p99
97.0s
Throughput
24 tps
Context
262K
$/Mtok
$0.770 / $3.40
siliconflow/fp8fp8
StreamLake100%
Healthy24h 98.36%
p50
1.41s
p99
10.7s
Throughput
26 tps
Context
256K
$/Mtok
$0.598 / $2.52
streamlake/fp8fp8
Together100%
Healthy24h 91.17%
p50
370ms
p99
6.14s
Throughput
115 tps
Context
262K
$/Mtok
$1.20 / $4.50
together
Venice100%
Healthy24h 80.65%
p50
1.07s
p99
7.22s
Throughput
18 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/int4int4
Decart99.80%
Healthy24h 97.70%
p50
539ms
p99
7.07s
Throughput
74 tps
Context
262K
$/Mtok
$0.568 / $3.33
decart/fp4fp4
CoreWeave99.39%
Healthy24h 99.14%
p50
379ms
p99
5.31s
Throughput
144 tps
Context
262K
$/Mtok
$0.650 / $3.41
coreweave/fp4fp4
Phala98.08%
Healthy24h 99.55%
p50
1.42s
p99
10.6s
Throughput
20 tps
Context
262K
$/Mtok
$1.09 / $4.60
phala
BaseTen—
No data24h —
p50
3.76s
p99
5.70s
Throughput
67 tps
Context
262K
$/Mtok
$0.950 / $4.00
baseten/fp4fp4
Fireworks—
No data24h 0.00%
p50
494ms
p99
6.25s
Throughput
73 tps
Context
262K
$/Mtok
$0.950 / $4.00
fireworks

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

2 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, averaged over the hour.

Throughput

Median tokens per second.