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%	99.77%	695ms	11.0s	106 tps	262K	$0.710 / $3.50
Parasailparasail/int4int4	Healthy	100%	97.97%	2.54s	22.4s	35 tps	262K	$0.760 / $3.50
Inceptroninceptron/int4int4	Healthy	99.49%	99.82%	872ms	178s	56 tps	262K	$0.670 / $3.40
ModelRunmodelrun/fp4fp4	Down	89.77%	94.67%	548ms	7.54s	164 tps	262K	$0.850 / $3.75
Alibabaalibaba/fp8fp8	No data	—	99.98%	3.23s	12.8s	34 tps	262K	$0.950 / $4.00
Ambientambient	No data	—	95.96%	1.32s	12.6s	44 tps	262K	$0.690 / $3.49
AtlasCloudatlas-cloud/int4int4	No data	—	99.81%	713ms	3.82s	73 tps	262K	$0.950 / $4.00
Cloudflarecloudflare	No data	—	99.93%	3.60s	12.8s	26 tps	262K	$0.950 / $4.00
DeepInfradeepinfra/fp4fp4	No data	—	98.20%	568ms	4.17s	47 tps	262K	$0.680 / $3.40
Moonshot AImoonshotai/highspeedint4	No data	—	99.97%	1.90s	9.41s	103 tps	262K	$1.90 / $8.00
Moonshot AImoonshotai/int4int4	No data	—	98.86%	6.70s	101s	40 tps	262K	$0.950 / $4.00
Novitanovita/int4int4	No data	—	97.96%	2.53s	19.1s	25 tps	262K	$0.912 / $3.84
SiliconFlowsiliconflow/fp8fp8	No data	—	99.94%	972ms	6.05s	48 tps	262K	$0.859 / $3.80
Togethertogether	Down	—	82.00%	4.12s	10.8s	181 tps	262K	$0.950 / $4.00
Venicevenice/int4int4	No data	—	93.57%	1.05s	6.71s	48 tps	256K	$0.750 / $3.50

CoreWeave100%
Healthy24h 99.77%
p50
695ms
p99
11.0s
Throughput
106 tps
Context
262K
$/Mtok
$0.710 / $3.50
coreweave/int4int4
Parasail100%
Healthy24h 97.97%
p50
2.54s
p99
22.4s
Throughput
35 tps
Context
262K
$/Mtok
$0.760 / $3.50
parasail/int4int4
Inceptron99.49%
Healthy24h 99.82%
p50
872ms
p99
178s
Throughput
56 tps
Context
262K
$/Mtok
$0.670 / $3.40
inceptron/int4int4
ModelRun89.77%
Down24h 94.67%
p50
548ms
p99
7.54s
Throughput
164 tps
Context
262K
$/Mtok
$0.850 / $3.75
modelrun/fp4fp4
Alibaba—
No data24h 99.98%
p50
3.23s
p99
12.8s
Throughput
34 tps
Context
262K
$/Mtok
$0.950 / $4.00
alibaba/fp8fp8
Ambient—
No data24h 95.96%
p50
1.32s
p99
12.6s
Throughput
44 tps
Context
262K
$/Mtok
$0.690 / $3.49
ambient
AtlasCloud—
No data24h 99.81%
p50
713ms
p99
3.82s
Throughput
73 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
Cloudflare—
No data24h 99.93%
p50
3.60s
p99
12.8s
Throughput
26 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
DeepInfra—
No data24h 98.20%
p50
568ms
p99
4.17s
Throughput
47 tps
Context
262K
$/Mtok
$0.680 / $3.40
deepinfra/fp4fp4
Moonshot AI—
No data24h 99.97%
p50
1.90s
p99
9.41s
Throughput
103 tps
Context
262K
$/Mtok
$1.90 / $8.00
moonshotai/highspeedint4
Moonshot AI—
No data24h 98.86%
p50
6.70s
p99
101s
Throughput
40 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
Novita—
No data24h 97.96%
p50
2.53s
p99
19.1s
Throughput
25 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
SiliconFlow—
No data24h 99.94%
p50
972ms
p99
6.05s
Throughput
48 tps
Context
262K
$/Mtok
$0.859 / $3.80
siliconflow/fp8fp8
Together—
Down24h 82.00%
p50
4.12s
p99
10.8s
Throughput
181 tps
Context
262K
$/Mtok
$0.950 / $4.00
together
Venice—
No data24h 93.57%
p50
1.05s
p99
6.71s
Throughput
48 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/int4int4

Measured 57s 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.

Throughput

Median tokens per second.