PrimeIntellect

15 endpoints · 1 unhealthy · worst uptime 20.00%

	State
DeepSeek V4 Flash 0731primeintellect/fp4fp4	Healthy	100%	99.08%	99.62%	99.62%	623ms	9.55s	108 tps	1.0M	$0.090 / $0.230
DeepSeek V4.1 Flashprimeintellect	Healthy	100%	99.33%	99.94%	98.12%	989ms	25.2s	88 tps	1.0M	$0.156 / $1.20
DeepSeek V4.1 Flash 1017primeintellect	Healthy	100%	100%	99.97%	99.84%	707ms	3.57s	186 tps	1.0M	$0.109 / $1.20
Gemma 4 26B A4B primeintellect/bf16bf16	Healthy	100%	100%	98.59%	99.15%	584ms	4.00s	46 tps	262K	$0.042 / $0.126
Nemotron 3.5 Super VLprimeintellect/nvfp4nvfp4	Healthy	100%	100%	99.44%	99.51%	2.74s	9.67s	205 tps	1.0M	$0.150 / $0.500
gpt-oss-120bprimeintellect/fp4fp4	Healthy	100%	100%	99.76%	99.76%	797ms	3.13s	64 tps	131K	$0.033 / $0.121
gpt-oss-20bprimeintellect/fp4fp4	Healthy	100%	100%	99.70%	99.70%	323ms	2.55s	112 tps	131K	$0.004 / $0.018
Qwen3.5-9Bprimeintellect/bf16bf16	Healthy	100%	99.72%	99.52%	99.64%	1.18s	11.9s	34 tps	262K	$0.032 / $0.047
Qwen3.6 35B A3Bprimeintellect/fp8fp8	Healthy	100%	99.79%	99.94%	99.94%	801ms	10.3s	72 tps	262K	$0.010 / $0.092
GLM 5.3primeintellect	Healthy	100%	99.73%	99.90%	99.79%	638ms	6.49s	55 tps	1.0M	$0.500 / $3.08
GLM 5.3 Flashprimeintellect	Healthy	100%	99.79%	99.87%	99.77%	645ms	3.51s	158 tps	1.0M	$0.150 / $0.500
Qwen3.8 27Bprimeintellect/fp8fp8	Down	20.00%	98.53%	96.81%	96.92%	802ms	17.5s	20 tps	131K	$0.024 / $1.32
Gemma 4 31Bprimeintellect/fp4fp4	No data	—	97.68%	96.18%	96.18%	352ms	1.89s	59 tps	262K	$0.400 / $0.670
Moondream 3 Previewprimeintellect/fp8fp8	No data	—	100%	99.35%	99.68%	199ms	895ms	291 tps	32K	$0.300 / $2.50
Moondream 3.1primeintellect/fp8fp8	No data	—	100%	97.18%	98.58%	255ms	647ms	282 tps	32K	$0.300 / $2.50

DeepSeek V4 Flash 0731100%
Healthy24h 99.08%
7d
99.62%
30d
99.62%
p50
623ms
p99
9.55s
Throughput
108 tps
Context
1.0M
$/Mtok
$0.090 / $0.230
primeintellect/fp4fp4
DeepSeek V4.1 Flash100%
Healthy24h 99.33%
7d
99.94%
30d
98.12%
p50
989ms
p99
25.2s
Throughput
88 tps
Context
1.0M
$/Mtok
$0.156 / $1.20
primeintellect
DeepSeek V4.1 Flash 1017100%
Healthy24h 100%
7d
99.97%
30d
99.84%
p50
707ms
p99
3.57s
Throughput
186 tps
Context
1.0M
$/Mtok
$0.109 / $1.20
primeintellect
Gemma 4 26B A4B 100%
Healthy24h 100%
7d
98.59%
30d
99.15%
p50
584ms
p99
4.00s
Throughput
46 tps
Context
262K
$/Mtok
$0.042 / $0.126
primeintellect/bf16bf16
Nemotron 3.5 Super VL100%
Healthy24h 100%
7d
99.44%
30d
99.51%
p50
2.74s
p99
9.67s
Throughput
205 tps
Context
1.0M
$/Mtok
$0.150 / $0.500
primeintellect/nvfp4nvfp4
gpt-oss-120b100%
Healthy24h 100%
7d
99.76%
30d
99.76%
p50
797ms
p99
3.13s
Throughput
64 tps
Context
131K
$/Mtok
$0.033 / $0.121
primeintellect/fp4fp4
gpt-oss-20b100%
Healthy24h 100%
7d
99.70%
30d
99.70%
p50
323ms
p99
2.55s
Throughput
112 tps
Context
131K
$/Mtok
$0.004 / $0.018
primeintellect/fp4fp4
Qwen3.5-9B100%
Healthy24h 99.72%
7d
99.52%
30d
99.64%
p50
1.18s
p99
11.9s
Throughput
34 tps
Context
262K
$/Mtok
$0.032 / $0.047
primeintellect/bf16bf16
Qwen3.6 35B A3B100%
Healthy24h 99.79%
7d
99.94%
30d
99.94%
p50
801ms
p99
10.3s
Throughput
72 tps
Context
262K
$/Mtok
$0.010 / $0.092
primeintellect/fp8fp8
GLM 5.3100%
Healthy24h 99.73%
7d
99.90%
30d
99.79%
p50
638ms
p99
6.49s
Throughput
55 tps
Context
1.0M
$/Mtok
$0.500 / $3.08
primeintellect
GLM 5.3 Flash100%
Healthy24h 99.79%
7d
99.87%
30d
99.77%
p50
645ms
p99
3.51s
Throughput
158 tps
Context
1.0M
$/Mtok
$0.150 / $0.500
primeintellect
Qwen3.8 27B20.00%
Down24h 98.53%
7d
96.81%
30d
96.92%
p50
802ms
p99
17.5s
Throughput
20 tps
Context
131K
$/Mtok
$0.024 / $1.32
primeintellect/fp8fp8
Gemma 4 31B—
No data24h 97.68%
7d
96.18%
30d
96.18%
p50
352ms
p99
1.89s
Throughput
59 tps
Context
262K
$/Mtok
$0.400 / $0.670
primeintellect/fp4fp4
Moondream 3 Preview—
No data24h 100%
7d
99.35%
30d
99.68%
p50
199ms
p99
895ms
Throughput
291 tps
Context
32K
$/Mtok
$0.300 / $2.50
primeintellect/fp8fp8
Moondream 3.1—
No data24h 100%
7d
97.18%
30d
98.58%
p50
255ms
p99
647ms
Throughput
282 tps
Context
32K
$/Mtok
$0.300 / $2.50
primeintellect/fp8fp8