Kimi K2.7 Code

moonshotai/kimi-k2.7-code

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

Provider	State	Uptime 5m	24h	p50 latency	p99	Throughput	Context	$/Mtok
Alibabaalibaba/fp8fp8	Healthy	100%	99.96%	3.73s	11.7s	27 tps	262K	$0.950 / $4.00
CoreWeavecoreweave/int4int4	Healthy	100%	99.77%	3.89s	28.7s	35 tps	262K	$0.710 / $3.50
DeepInfradeepinfra/fp4fp4	Healthy	100%	98.12%	585ms	7.84s	56 tps	262K	$0.680 / $3.40
Inceptroninceptron/int4int4	Healthy	100%	99.84%	925ms	81.9s	50 tps	262K	$0.670 / $3.40
Moonshot AImoonshotai/highspeedint4	Healthy	100%	99.97%	2.17s	9.62s	98 tps	262K	$1.90 / $8.00
Moonshot AImoonshotai/int4int4	Healthy	98.98%	98.84%	2.30s	24.3s	29 tps	262K	$0.950 / $4.00
ModelRunmodelrun/fp4fp4	Down	88.52%	95.83%	527ms	12.0s	174 tps	262K	$0.850 / $3.75
Togethertogether	Down	84.09%	85.50%	434ms	10.4s	189 tps	262K	$0.950 / $4.00
Ambientambient	No data	—	95.81%	716ms	4.85s	98 tps	262K	$0.690 / $3.49
AtlasCloudatlas-cloud/int4int4	No data	—	99.82%	1.07s	12.4s	66 tps	262K	$0.950 / $4.00
Cloudflarecloudflare	No data	—	99.93%	1.94s	19.8s	42 tps	262K	$0.950 / $4.00
Novitanovita/int4int4	No data	—	97.99%	1.99s	16.2s	28 tps	262K	$0.912 / $3.84
Parasailparasail/int4int4	No data	—	97.97%	1.23s	11.8s	46 tps	262K	$0.760 / $3.50
SiliconFlowsiliconflow/fp8fp8	No data	—	99.94%	1.34s	3.39s	46 tps	262K	$0.859 / $3.80
Venicevenice/int4int4	No data	—	92.71%	1.04s	7.71s	47 tps	256K	$0.750 / $3.50

Alibaba100%
Healthy24h 99.96%
p50
3.73s
p99
11.7s
Throughput
27 tps
Context
262K
$/Mtok
$0.950 / $4.00
alibaba/fp8fp8
CoreWeave100%
Healthy24h 99.77%
p50
3.89s
p99
28.7s
Throughput
35 tps
Context
262K
$/Mtok
$0.710 / $3.50
coreweave/int4int4
DeepInfra100%
Healthy24h 98.12%
p50
585ms
p99
7.84s
Throughput
56 tps
Context
262K
$/Mtok
$0.680 / $3.40
deepinfra/fp4fp4
Inceptron100%
Healthy24h 99.84%
p50
925ms
p99
81.9s
Throughput
50 tps
Context
262K
$/Mtok
$0.670 / $3.40
inceptron/int4int4
Moonshot AI100%
Healthy24h 99.97%
p50
2.17s
p99
9.62s
Throughput
98 tps
Context
262K
$/Mtok
$1.90 / $8.00
moonshotai/highspeedint4
Moonshot AI98.98%
Healthy24h 98.84%
p50
2.30s
p99
24.3s
Throughput
29 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
ModelRun88.52%
Down24h 95.83%
p50
527ms
p99
12.0s
Throughput
174 tps
Context
262K
$/Mtok
$0.850 / $3.75
modelrun/fp4fp4
Together84.09%
Down24h 85.50%
p50
434ms
p99
10.4s
Throughput
189 tps
Context
262K
$/Mtok
$0.950 / $4.00
together
Ambient—
No data24h 95.81%
p50
716ms
p99
4.85s
Throughput
98 tps
Context
262K
$/Mtok
$0.690 / $3.49
ambient
AtlasCloud—
No data24h 99.82%
p50
1.07s
p99
12.4s
Throughput
66 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
Cloudflare—
No data24h 99.93%
p50
1.94s
p99
19.8s
Throughput
42 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
Novita—
No data24h 97.99%
p50
1.99s
p99
16.2s
Throughput
28 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
Parasail—
No data24h 97.97%
p50
1.23s
p99
11.8s
Throughput
46 tps
Context
262K
$/Mtok
$0.760 / $3.50
parasail/int4int4
SiliconFlow—
No data24h 99.94%
p50
1.34s
p99
3.39s
Throughput
46 tps
Context
262K
$/Mtok
$0.859 / $3.80
siliconflow/fp8fp8
Venice—
No data24h 92.71%
p50
1.04s
p99
7.71s
Throughput
47 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/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.