Kimi K2.6: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
Cloudflarecloudflare	Healthy	100%◆ (best)	99.98%	87.44%	87.44%	700ms	5.48s	41 tps	262K	$0.950 / $4.00
Inceptroninceptron/int4int4	Healthy	100%◆ (best)	99.68%	99.45%	99.45%	766ms	7.82s	48 tps	262K	$0.600 / $3.41
Moonshot AImoonshotai/int4int4	Healthy	100%◆ (best)	99.97%	99.91%◆ (best)	99.91%◆ (best)	2.26s	32.4s	31 tps	262K	$0.950 / $4.00
Novitanovita	Healthy	100%◆ (best)	99.75%	99.67%	99.67%	1.33s	16.4s	27 tps	262K	$0.800 / $3.40
Parasailparasail/int4int4	Healthy	100%◆ (best)	99.61%	99.11%	99.11%	925ms	10.5s	76 tps	262K	$0.750 / $3.50
SiliconFlowsiliconflow/fp8fp8	Healthy	100%◆ (best)	99.82%	99.81%	99.81%	1.13s	8.54s	44 tps	262K	$0.770 / $3.40
StreamLakestreamlake/fp8fp8	Healthy	100%◆ (best)	97.88%	98.23%	98.23%	1.69s	23.4s	38 tps	256K	$0.598 / $2.52
Venicevenice/int4int4	Healthy	100%◆ (best)	96.16%	96.52%	96.52%	1.33s	10.4s	17 tps	256K	$0.750 / $3.50
Decartdecart/fp4fp4	Healthy	99.51%	98.12%	97.54%	97.54%	664ms	8.56s	64 tps	262K	$0.568 / $2.39◆ (best)
Baidubaidu/fp4fp4	Healthy	99.43%	99.84%	99.82%	99.82%	1.67s	10.2s	50 tps	262K	$0.580 / $2.44
DeepInfradeepinfra/fp4fp4	Healthy	98.06%	99.73%	99.15%	99.15%	1.07s	8.24s	15 tps	262K	$0.750 / $3.50
CoreWeavecoreweave/fp4fp4	Healthy	97.75%	99.33%	99.42%	99.42%	949ms	12.6s	123 tps◆ (best)	262K	$0.650 / $3.41
Chuteschutes/int4int4	Healthy	95.16%	98.17%	98.35%	98.35%	2.31s	38.9s	39 tps	262K	$0.580 / $3.40
AtlasCloudatlas-cloud/int4int4	No data	—	95.96%	96.19%	96.19%	2.48s	15.5s	29 tps	262K	$0.950 / $4.00
BaseTenbaseten/fp4fp4	No data	—	—	—	—	852ms	4.27s◆ (best)	81 tps	262K	$0.950 / $4.00
Crusoecrusoe/bf16bf16	Down	—	90.79%	88.17%	88.17%	813ms	112s	8.0 tps	262K	$0.700 / $3.50
DigitalOceandigitalocean	Down	—	98.92%	98.98%	98.98%	2.57s	51.5s	15 tps	262K	$0.950 / $4.00
Fireworksfireworks	No data	—	82.26%	96.85%	96.85%	480ms◆ (best)	6.02s	75 tps	262K	$0.950 / $4.00
Phalaphala	No data	—	98.58%	98.28%	98.28%	2.06s	12.9s	19 tps	262K	$1.09 / $4.60
Sail Researchsail-research/int4int4	No data	—	—	99.88%	99.88%	—	—	—	262K	$1.00 / $4.00
Togethertogether	No data	—	—	97.92%	97.92%	—	—	—	262K	$1.20 / $4.50

Cloudflare100%◆ (best)
Healthy24h 99.98%
7d
87.44%
30d
87.44%
p50
700ms
p99
5.48s
Throughput
41 tps
Context
262K
$/Mtok
$0.950 / $4.00
cloudflare
Inceptron100%◆ (best)
Healthy24h 99.68%
7d
99.45%
30d
99.45%
p50
766ms
p99
7.82s
Throughput
48 tps
Context
262K
$/Mtok
$0.600 / $3.41
inceptron/int4int4
Moonshot AI100%◆ (best)
Healthy24h 99.97%
7d
99.91%◆ (best)
30d
99.91%◆ (best)
p50
2.26s
p99
32.4s
Throughput
31 tps
Context
262K
$/Mtok
$0.950 / $4.00
moonshotai/int4int4
Novita100%◆ (best)
Healthy24h 99.75%
7d
99.67%
30d
99.67%
p50
1.33s
p99
16.4s
Throughput
27 tps
Context
262K
$/Mtok
$0.800 / $3.40
novita
Parasail100%◆ (best)
Healthy24h 99.61%
7d
99.11%
30d
99.11%
p50
925ms
p99
10.5s
Throughput
76 tps
Context
262K
$/Mtok
$0.750 / $3.50
parasail/int4int4
SiliconFlow100%◆ (best)
Healthy24h 99.82%
7d
99.81%
30d
99.81%
p50
1.13s
p99
8.54s
Throughput
44 tps
Context
262K
$/Mtok
$0.770 / $3.40
siliconflow/fp8fp8
StreamLake100%◆ (best)
Healthy24h 97.88%
7d
98.23%
30d
98.23%
p50
1.69s
p99
23.4s
Throughput
38 tps
Context
256K
$/Mtok
$0.598 / $2.52
streamlake/fp8fp8
Venice100%◆ (best)
Healthy24h 96.16%
7d
96.52%
30d
96.52%
p50
1.33s
p99
10.4s
Throughput
17 tps
Context
256K
$/Mtok
$0.750 / $3.50
venice/int4int4
Decart99.51%
Healthy24h 98.12%
7d
97.54%
30d
97.54%
p50
664ms
p99
8.56s
Throughput
64 tps
Context
262K
$/Mtok
$0.568 / $2.39◆ (best)
decart/fp4fp4
Baidu99.43%
Healthy24h 99.84%
7d
99.82%
30d
99.82%
p50
1.67s
p99
10.2s
Throughput
50 tps
Context
262K
$/Mtok
$0.580 / $2.44
baidu/fp4fp4
DeepInfra98.06%
Healthy24h 99.73%
7d
99.15%
30d
99.15%
p50
1.07s
p99
8.24s
Throughput
15 tps
Context
262K
$/Mtok
$0.750 / $3.50
deepinfra/fp4fp4
CoreWeave97.75%
Healthy24h 99.33%
7d
99.42%
30d
99.42%
p50
949ms
p99
12.6s
Throughput
123 tps◆ (best)
Context
262K
$/Mtok
$0.650 / $3.41
coreweave/fp4fp4
Chutes95.16%
Healthy24h 98.17%
7d
98.35%
30d
98.35%
p50
2.31s
p99
38.9s
Throughput
39 tps
Context
262K
$/Mtok
$0.580 / $3.40
chutes/int4int4
AtlasCloud—
No data24h 95.96%
7d
96.19%
30d
96.19%
p50
2.48s
p99
15.5s
Throughput
29 tps
Context
262K
$/Mtok
$0.950 / $4.00
atlas-cloud/int4int4
BaseTen—
No data24h —
7d
—
30d
—
p50
852ms
p99
4.27s◆ (best)
Throughput
81 tps
Context
262K
$/Mtok
$0.950 / $4.00
baseten/fp4fp4
Crusoe—
Down24h 90.79%
7d
88.17%
30d
88.17%
p50
813ms
p99
112s
Throughput
8.0 tps
Context
262K
$/Mtok
$0.700 / $3.50
crusoe/bf16bf16
DigitalOcean—
Down24h 98.92%
7d
98.98%
30d
98.98%
p50
2.57s
p99
51.5s
Throughput
15 tps
Context
262K
$/Mtok
$0.950 / $4.00
digitalocean
Fireworks—
No data24h 82.26%
7d
96.85%
30d
96.85%
p50
480ms◆ (best)
p99
6.02s
Throughput
75 tps
Context
262K
$/Mtok
$0.950 / $4.00
fireworks
Phala—
No data24h 98.58%
7d
98.28%
30d
98.28%
p50
2.06s
p99
12.9s
Throughput
19 tps
Context
262K
$/Mtok
$1.09 / $4.60
phala
Sail Research—
No data24h —
7d
99.88%
30d
99.88%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$1.00 / $4.00
sail-research/int4int4
Together—
No data24h —
7d
97.92%
30d
97.92%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$1.20 / $4.50
together

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.