Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Compare with Kimi K2.6, Kimi K2.5, Kimi K3

CompareKimi K2.7 Code

Provider	State	Uptime 5m	24h	p50 latency	p99	Throughput	Context	$/Mtok
CoreWeavecoreweave/int4int4	Healthy	100%	99.75%	1.52s	16.9s	81 tps	262K	$0.710 / $3.50
Inceptroninceptron/int4int4	Healthy	100%	99.80%	879ms	160s	64 tps	262K	$0.670 / $3.40
Moonshot AImoonshotai/highspeedint4	Healthy	100%	99.97%	2.38s	9.87s	90 tps	262K	$1.90 / $8.00
Moonshot AImoonshotai/int4int4	Healthy	100%	98.86%	5.83s	53.8s	33 tps	262K	$0.950 / $4.00
Alibabaalibaba/fp8fp8	No data	—	99.98%	3.93s	12.4s	30 tps	262K	$0.950 / $4.00
Ambientambient	No data	—	94.21%	1.15s	10.9s	97 tps	262K	$0.690 / $3.49
AtlasCloudatlas-cloud/int4int4	No data	—	99.84%	1.06s	7.84s	62 tps	262K	$0.950 / $4.00
Cloudflarecloudflare	No data	—	99.95%	817ms	20.7s	34 tps	262K	$0.950 / $4.00
DeepInfradeepinfra/fp4fp4	No data	—	98.20%	566ms	6.22s	26 tps	262K	$0.680 / $3.40
GMICloudgmicloud/fp8fp8	No data	—	—	5.73s	10.7s	26 tps	262K	$0.950 / $4.00
ModelRunmodelrun/fp4fp4	Down	—	90.32%	682ms	8.81s	155 tps	262K	$0.850 / $3.75
Novitanovita/int4int4	No data	—	97.77%	2.88s	18.1s	26 tps	262K	$0.912 / $3.84
Parasailparasail/int4int4	No data	—	97.79%	1.12s	13.5s	58 tps	262K	$0.760 / $3.50
SiliconFlowsiliconflow/fp8fp8	No data	—	99.94%	1.50s	3.89s	50 tps	262K	$0.859 / $3.80
Togethertogether	Down	—	73.26%	596ms	4.88s	144 tps	262K	$0.950 / $4.00
Venicevenice/int4int4	No data	—	94.80%	1.08s	15.1s	21 tps	256K	$0.750 / $3.50

CoreWeave100%
Healthy24h 99.75%
p50
1.52s
p99
16.9s
Throughput
81 tps
Context
262K
$/Mtok
$0.710 / $3.50
coreweave/int4int4
Inceptron100%
Healthy24h 99.80%
p50
879ms
p99
160s
Throughput
64 tps
Context
262K
$/Mtok
$0.670 / $3.40
inceptron/int4int4
Moonshot AI100%
Healthy24h 99.97%
p50
2.38s
p99
9.87s
Throughput
90 tps
Context
262K
$/Mtok
$1.90 / $8.00
moonshotai/highspeedint4
Moonshot AI100%
Healthy24h 98.86%
p50
5.83s
p99
53.8s
Throughput
33 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
Alibaba—
No data24h 99.98%
p50
3.93s
p99
12.4s
Throughput
30 tps
Context
262K
$/Mtok
$0.950 / $4.00
alibaba/fp8fp8
Ambient—
No data24h 94.21%
p50
1.15s
p99
10.9s
Throughput
97 tps
Context
262K
$/Mtok
$0.690 / $3.49
ambient
AtlasCloud—
No data24h 99.84%
p50
1.06s
p99
7.84s
Throughput
62 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
Cloudflare—
No data24h 99.95%
p50
817ms
p99
20.7s
Throughput
34 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
DeepInfra—
No data24h 98.20%
p50
566ms
p99
6.22s
Throughput
26 tps
Context
262K
$/Mtok
$0.680 / $3.40
deepinfra/fp4fp4
GMICloud—
No data24h —
p50
5.73s
p99
10.7s
Throughput
26 tps
Context
262K
$/Mtok
$0.950 / $4.00
gmicloud/fp8fp8
ModelRun—
Down24h 90.32%
p50
682ms
p99
8.81s
Throughput
155 tps
Context
262K
$/Mtok
$0.850 / $3.75
modelrun/fp4fp4
Novita—
No data24h 97.77%
p50
2.88s
p99
18.1s
Throughput
26 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
Parasail—
No data24h 97.79%
p50
1.12s
p99
13.5s
Throughput
58 tps
Context
262K
$/Mtok
$0.760 / $3.50
parasail/int4int4
SiliconFlow—
No data24h 99.94%
p50
1.50s
p99
3.89s
Throughput
50 tps
Context
262K
$/Mtok
$0.859 / $3.80
siliconflow/fp8fp8
Together—
Down24h 73.26%
p50
596ms
p99
4.88s
Throughput
144 tps
Context
262K
$/Mtok
$0.950 / $4.00
together
Venice—
No data24h 94.80%
p50
1.08s
p99
15.1s
Throughput
21 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/int4int4

Measured 44s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

10 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.