API host · catalogue checked 27 Oct 2026

StreamLake: models, prices and uptime

StreamLake serves 8 of the 78 models we benchmark through OpenRouter. Prices are OpenRouter's list prices per million tokens. We did not measure speed per host.

Models served8of 78 we test

Cheapest host for0of 8 shared models

Median premium+48%over the cheapest host

Uptime92.9%last 30 min, average

Most accurate models on StreamLake

Verification score of each model this host serves

1DeepSeek V4.1 Flash 1017DeepSeek73.8%
2DeepSeek V4 Pro 0813DeepSeek71.2%
3MiMo-V2.6-ProXiaomi68.8%
4GLM 5.3 FlashZ.ai67.5%
5MiniMax M3.1 FlashMiniMax66.2%
6Kimi K2.7 CodeMoonshotAI65.0%
7MiniMax M3MiniMax57.5%
8Qwen3.5 397B A17BQwen32.5%

Models on StreamLake

Premium: this host's blended price (3 input : 1 output) against the cheapest host for the same model

Model	Score	Input / 1M	Output / 1M	vs cheapest host	Hosts	Context	Max output	Quantization	Uptime
DeepSeek V4.1 Flash 1017	73.8%	$0.1785	$0.714	+176%	30	1M	384k	fp8	100%
DeepSeek V4 Pro 0813	71.2%	$0.66	$1.98	+372%	23	1M	384k	—	100%
MiMo-V2.6-Pro	68.8%	$0.522	$1.044	+41%	5	1M	128k	—	50.0%
GLM 5.3 Flash	67.5%	$0.0885	$0.295	+199%	34	1M	128k	fp8	100%
MiniMax M3.1 Flash	66.2%	$0.15	$0.6	+5%	11	1M	512k	—	—
Kimi K2.7 Code	65.0%	$0.7125	$3	+7%	11	256k	32k	—	100%
MiniMax M3	57.5%	$0.3	$1.2	+35%	12	1M	512k	fp8	100%
Qwen3.5 397B A17B	32.5%	$0.6	$3.6	+54%	10	256k	64k	—	100%

All API hosts →

StreamLake: frequently asked questions

Which AI models does StreamLake serve?: Of the models we benchmark, StreamLake serves 8 through OpenRouter: DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, MiMo-V2.6-Pro, GLM 5.3 Flash, MiniMax M3.1 Flash, Kimi K2.7 Code, MiniMax M3, Qwen3.5 397B A17B.
What is the most accurate model on StreamLake?: DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.
Is StreamLake the cheapest host?: StreamLake has the lowest list price for 0 of the 8 models it serves that other hosts also serve. Its median markup over the cheapest host is +48%.
How reliable is StreamLake?: Averaged over the models it serves, StreamLake reported 92.9% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

Model

Score

Input / 1M

Output / 1M

vs cheapest host

Hosts

Context

Max output

Quantization

Uptime

DeepSeek V4.1 Flash 1017

73.8%

$0.1785

$0.714

+176%

384k

fp8

100%

DeepSeek V4 Pro 0813

71.2%

$0.66

$1.98

+372%

384k

—

100%

MiMo-V2.6-Pro

68.8%

$0.522

$1.044

+41%

128k

—

50.0%

GLM 5.3 Flash

67.5%

$0.0885

$0.295

+199%

128k

fp8

100%

MiniMax M3.1 Flash

66.2%

$0.15

$0.6

+5%

512k

—

Kimi K2.7 Code

65.0%

$0.7125

+7%

256k

32k

—

100%

MiniMax M3

57.5%

$0.3

$1.2

+35%

512k

fp8

100%

Qwen3.5 397B A17B

32.5%

$0.6

$3.6

+54%

256k

64k

—

100%

StreamLake: frequently asked questions

Which AI models does StreamLake serve?

Of the models we benchmark, StreamLake serves 8 through OpenRouter: DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, MiMo-V2.6-Pro, GLM 5.3 Flash, MiniMax M3.1 Flash, Kimi K2.7 Code, MiniMax M3, Qwen3.5 397B A17B.

What is the most accurate model on StreamLake?

DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.

Is StreamLake the cheapest host?

StreamLake has the lowest list price for 0 of the 8 models it serves that other hosts also serve. Its median markup over the cheapest host is +48%.

How reliable is StreamLake?

Averaged over the models it serves, StreamLake reported 92.9% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.