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
Alibabaalibaba/fp8fp8	Healthy	100%	99.98%	3.52s	9.63s	31 tps	262K	$0.950 / $4.00
DeepInfradeepinfra/fp4fp4	Healthy	100%	98.19%	673ms	7.54s	31 tps	262K	$0.680 / $3.40
Inceptroninceptron/int4int4	Healthy	100%	99.80%	839ms	107s	59 tps	262K	$0.670 / $3.40
Moonshot AImoonshotai/highspeedint4	Healthy	100%	99.97%	2.06s	13.9s	95 tps	262K	$1.90 / $8.00
Moonshot AImoonshotai/int4int4	Healthy	100%	98.83%	5.95s	67.3s	38 tps	262K	$0.950 / $4.00
SiliconFlowsiliconflow/fp8fp8	Healthy	100%	99.94%	1.22s	8.01s	36 tps	262K	$0.859 / $3.80
Venicevenice/int4int4	Healthy	100%	94.28%	928ms	8.41s	27 tps	256K	$0.750 / $3.50
CoreWeavecoreweave/int4int4	Healthy	99.68%	99.76%	1.78s	20.3s	70 tps	262K	$0.710 / $3.50
ModelRunmodelrun/fp4fp4	Down	85.42%	91.45%	592ms	22.7s	183 tps	262K	$0.850 / $3.75
Ambientambient	No data	—	94.92%	1.28s	16.2s	65 tps	262K	$0.690 / $3.49
AtlasCloudatlas-cloud/int4int4	No data	—	99.85%	672ms	9.03s	67 tps	262K	$0.950 / $4.00
Cloudflarecloudflare	No data	—	99.95%	1.75s	35.7s	35 tps	262K	$0.950 / $4.00
Novitanovita/int4int4	No data	—	97.71%	1.48s	134s	41 tps	262K	$0.912 / $3.84
Parasailparasail/int4int4	No data	—	97.83%	1.10s	7.38s	56 tps	262K	$0.760 / $3.50
Togethertogether	Down	—	75.72%	772ms	10.9s	89 tps	262K	$0.950 / $4.00

Alibaba100%
Healthy24h 99.98%
p50
3.52s
p99
9.63s
Throughput
31 tps
Context
262K
$/Mtok
$0.950 / $4.00
alibaba/fp8fp8
DeepInfra100%
Healthy24h 98.19%
p50
673ms
p99
7.54s
Throughput
31 tps
Context
262K
$/Mtok
$0.680 / $3.40
deepinfra/fp4fp4
Inceptron100%
Healthy24h 99.80%
p50
839ms
p99
107s
Throughput
59 tps
Context
262K
$/Mtok
$0.670 / $3.40
inceptron/int4int4
Moonshot AI100%
Healthy24h 99.97%
p50
2.06s
p99
13.9s
Throughput
95 tps
Context
262K
$/Mtok
$1.90 / $8.00
moonshotai/highspeedint4
Moonshot AI100%
Healthy24h 98.83%
p50
5.95s
p99
67.3s
Throughput
38 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
SiliconFlow100%
Healthy24h 99.94%
p50
1.22s
p99
8.01s
Throughput
36 tps
Context
262K
$/Mtok
$0.859 / $3.80
siliconflow/fp8fp8
Venice100%
Healthy24h 94.28%
p50
928ms
p99
8.41s
Throughput
27 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/int4int4
CoreWeave99.68%
Healthy24h 99.76%
p50
1.78s
p99
20.3s
Throughput
70 tps
Context
262K
$/Mtok
$0.710 / $3.50
coreweave/int4int4
ModelRun85.42%
Down24h 91.45%
p50
592ms
p99
22.7s
Throughput
183 tps
Context
262K
$/Mtok
$0.850 / $3.75
modelrun/fp4fp4
Ambient—
No data24h 94.92%
p50
1.28s
p99
16.2s
Throughput
65 tps
Context
262K
$/Mtok
$0.690 / $3.49
ambient
AtlasCloud—
No data24h 99.85%
p50
672ms
p99
9.03s
Throughput
67 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
Cloudflare—
No data24h 99.95%
p50
1.75s
p99
35.7s
Throughput
35 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
Novita—
No data24h 97.71%
p50
1.48s
p99
134s
Throughput
41 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
Parasail—
No data24h 97.83%
p50
1.10s
p99
7.38s
Throughput
56 tps
Context
262K
$/Mtok
$0.760 / $3.50
parasail/int4int4
Together—
Down24h 75.72%
p50
772ms
p99
10.9s
Throughput
89 tps
Context
262K
$/Mtok
$0.950 / $4.00
together

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

5 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.