Novita

74 endpoints · 5 unhealthy · worst uptime 70.26%

	State
Apodex 1.1 Mini (free)novita/bf16bf16	Healthy	100%	99.99%	99.98%	99.98%	1.43s	6.09s	116 tps	262K	free / free
R1novita/fp8fp8	Healthy	100%	100%	100%	100%	1.18s	5.23s	20 tps	64K	$0.700 / $2.50
R1 0528novita/fp8fp8	Healthy	100%	99.89%	99.87%	99.82%	1.30s	5.53s	20 tps	164K	$0.700 / $2.50
DeepSeek V4 Flash 0731novita/fp8fp8	Healthy	100%	99.99%	99.99%	99.98%	1.28s	5.57s	50 tps	1.0M	$0.409 / $1.23
DeepSeek V4 Flash Vision Expnovita	Healthy	100%	99.97%	98.99%	99.41%	1.41s	4.79s	132 tps	1.0M	$0.440 / $1.32
DeepSeek V4 Pro 0423novita/fp8fp8	Healthy	100%	99.97%	99.94%	99.91%	2.48s	13.7s	58 tps	1.0M	$1.60 / $3.20
DeepSeek V4 Pro 0813novita/fp8fp8	Healthy	100%	99.97%	99.97%	99.92%	1.76s	4.67s	75 tps	1.0M	$0.990 / $2.97
DeepSeek V4.1 Flashnovita/fp8fp8	Healthy	100%	99.90%	99.81%	99.53%	1.84s	22.6s	70 tps	1.0M	$0.240 / $0.960
Gemma 3 27Bnovita/bf16bf16	Healthy	100%	96.53%	96.15%	94.13%	1.49s	4.90s	26 tps	98K	$0.119 / $0.200
Ling 3.0 Flashnovita	Healthy	100%	100%	100%	99.95%	1.09s	2.33s	186 tps	262K	$0.021 / $0.063
Ling 3.0 Flash Sante (free)novita	Healthy	100%	100%	100%	99.97%	1.15s	8.32s	161 tps	262K	free / free
Ling 3.1 Flashnovita	Healthy	100%	100%	100%	100%	2.44s	230s	60 tps	262K	free / free
Llama 4 Scoutnovita/bf16bf16	Healthy	100%	99.90%	99.92%	99.64%	741ms	2.51s	27 tps	131K	$0.180 / $0.590
WizardLM-2 8x22Bnovita/bf16bf16	Healthy	100%	99.99%	99.99%	100%	1.79s	7.05s	16 tps	66K	$0.620 / $0.620
MiniMax M2.7novita/fp8fp8	Healthy	100%	99.50%	99.56%	99.53%	1.65s	4.75s	49 tps	205K	$0.270 / $1.08
Mistral Nemonovita/fp8fp8	Down	100%	78.16%	81.08%	80.68%	550ms	28.4s	68 tps	60K	$0.040 / $0.170
Kimi K2 0711novita/fp8fp8	Healthy	100%	100%	100%	99.99%	794ms	34.9s	45 tps	131K	$0.570 / $2.30
Kimi K2 0905novita/fp8fp8	Healthy	100%	100%	100%	100%	725ms	6.94s	46 tps	262K	$0.600 / $2.50
Kimi K2 Thinkingnovita/bf16bf16	Healthy	100%	99.93%	99.78%	99.59%	1.81s	13.5s	47 tps	262K	$0.600 / $2.50
Kimi K2.6novita	Healthy	100%	99.95%	99.80%	99.27%	1.60s	41.4s	48 tps	262K	$0.800 / $3.40
Nemotron 3 Nano 30B A3Bnovita/fp4fp4	Healthy	100%	99.98%	99.69%	99.85%	455ms	6.71s	255 tps	262K	$0.050 / $0.200
gpt-oss-20bnovita/fp4fp4	Healthy	100%	99.94%	99.77%	99.77%	736ms	2.98s	102 tps	131K	$0.040 / $0.150
Qwen2.5 72B Instructnovita/bf16bf16	Healthy	100%	99.48%	95.85%	95.44%	697ms	3.74s	25 tps	32K	$0.380 / $0.400
Qwen3 235B A22B Instruct 2507novita/fp8fp8	Healthy	100%	95.55%	96.56%	97.88%	733ms	94.5s	53 tps	131K	$0.090 / $0.580
Qwen3 Coder 30B A3B Instructnovita/fp8fp8	Healthy	100%	97.39%	98.53%	97.81%	931ms	3.18s	51 tps	160K	$0.070 / $0.270
Qwen3 Coder Nextnovita/fp8fp8	Healthy	100%	99.64%	99.66%	99.63%	1.84s	9.59s	54 tps	262K	$0.200 / $1.50
Qwen3.5-122B-A10Bnovita/bf16bf16	Healthy	100%	99.57%	99.05%	99.59%	578ms	3.28s	108 tps	262K	$0.400 / $3.20
Qwen3.5-27Bnovita/bf16bf16	Healthy	100%	99.97%	99.96%	99.73%	979ms	5.10s	53 tps	262K	$0.300 / $2.40
Qwen3.8 2.4T A95Bnovita	Healthy	100%	99.94%	99.87%	99.90%	2.89s	22.6s	39 tps	1.0M	$2.00 / $6.00
Qwen3.8 27Bnovita	Healthy	100%	99.96%	99.81%	99.77%	6.79s	55.7s	49 tps	1.0M	$0.420 / $3.00
Llama 3 8B Lunarisnovita/bf16bf16	Healthy	100%	99.98%	99.98%	99.91%	320ms	1.61s	74 tps	8K	$0.050 / $0.050
Step 3.7 Flashnovita/fp8fp8	Healthy	100%	99.83%	99.74%	99.30%	3.87s	13.8s	90 tps	262K	$0.200 / $1.15
MiMo-V2.5novita/fp8fp8	Healthy	100%	97.80%	96.29%	96.71%	2.08s	21.9s	47 tps	1.0M	$0.168 / $0.336
GLM 4.5 Airnovita/bf16bf16	Healthy	100%	99.87%	99.84%	99.74%	831ms	11.9s	63 tps	131K	$0.130 / $0.850
GLM 4.6Vnovita/bf16bf16	Healthy	100%	99.86%	99.47%	97.80%	1.48s	7.90s	52 tps	131K	$0.300 / $0.900
GLM 4.7novita/fp8fp8	Healthy	100%	99.58%	99.66%	96.85%	4.16s	11.3s	27 tps	205K	$0.540 / $1.98
GLM 5novita/fp8fp8	Healthy	100%	100%	100%	99.97%	1.35s	9.66s	44 tps	203K	$1.00 / $3.20
GLM 5.2novita/fp8fp8	Healthy	100%	99.84%	99.73%	99.89%	1.53s	8.53s	53 tps	1.0M	$0.650 / $2.04
DeepSeek V4 Flash 0423novita/fp8fp8	Healthy	99.97%	99.96%	99.95%	99.93%	1.33s	6.91s	62 tps	1.0M	$0.140 / $0.280
Ling 3.0 Flash VLnovita/bf16bf16	Healthy	99.97%	99.95%	99.77%	99.77%	906ms	9.62s	119 tps	262K	$0.021 / $0.062
Gemma 4 31Bnovita/bf16bf16	Healthy	99.95%	91.81%	82.51%	88.92%	707ms	21.1s	18 tps	262K	$0.140 / $0.400
GLM 5.3 Flashnovita/fp8fp8	Healthy	99.92%	98.76%	99.06%	98.72%	1.72s	12.5s	46 tps	1.0M	$0.084 / $0.280
Llama 3.1 8B Instructnovita/fp8fp8	Healthy	99.88%	99.77%	99.26%	98.57%	498ms	3.10s	85 tps	16K	$0.020 / $0.050
Gemma 4 26B A4B novita/bf16bf16	Healthy	99.87%	99.90%	99.54%	99.49%	869ms	7.84s	76 tps	262K	$0.130 / $0.400
Llama 3.3 70B Instructnovita/bf16bf16	Healthy	99.84%	95.79%	92.96%	97.42%	1.24s	3.22s	33 tps	12K	$0.135 / $0.400
Qwen3 VL 30B A3B Instructnovita/bf16bf16	Healthy	99.47%	99.16%	98.82%	97.66%	776ms	5.49s	98 tps	131K	$0.200 / $0.700
MiMo-V2.6-Pronovita/fp8fp8	Healthy	99.28%	99.61%	99.59%	99.59%	4.35s	45.4s	35 tps	1.0M	$0.435 / $0.870
Llama 4 Mavericknovita/fp8fp8	Healthy	99.27%	99.07%	98.92%	99.39%	781ms	6.16s	23 tps	1.0M	$0.270 / $0.850
GLM 5.3novita/fp8fp8	Healthy	99.20%	99.08%	99.83%	99.57%	2.71s	82.3s	25 tps	1.0M	$0.420 / $1.32
GLM 4.6novita/bf16bf16	Healthy	98.89%	99.84%	98.83%	96.99%	4.31s	9.91s	27 tps	205K	$0.550 / $2.20
Kimi K2.5novita	Healthy	98.53%	98.59%	98.35%	96.93%	1.42s	13.4s	46 tps	262K	$0.570 / $2.85
MiMo-V2.5-Pronovita	Healthy	98.48%	98.81%	97.21%	95.58%	2.65s	48.9s	41 tps	1.0M	$0.480 / $0.960
gpt-oss-120bnovita/fp4fp4	Healthy	96.62%	98.82%	98.97%	92.00%	847ms	18.6s	69 tps	131K	$0.050 / $0.250
MiMo-V2.6-Flashnovita/fp8fp8	Healthy	96.39%	96.82%	96.20%	96.20%	2.91s	27.6s	30 tps	1.0M	$0.140 / $0.280
Qwen3 Next 80B A3B Instructnovita/bf16bf16	Degraded	91.24%	85.37%	88.89%	93.46%	1.48s	61.8s	85 tps	131K	$0.150 / $1.50
GLM 4.7 Flashnovita/bf16bf16	Down	70.26%	65.95%	67.16%	67.74%	847ms	27.2s	68 tps	200K	$0.070 / $0.400
ERNIE 4.5 VL 424B A47B novita/fp16fp16	No data	—	100%	100%	100%	1.83s	13.7s	25 tps	123K	$0.420 / $1.25
Ling 3.0 Flash Finnovita	No data	—	100%	99.98%	99.98%	914ms	12.2s	141 tps	262K	$0.042 / $0.123
MiniMax M1novita/bf16bf16	No data	—	100%	100%	100%	1.22s	3.00s	54 tps	1.0M	$0.550 / $2.20
MiniMax M2novita/fp8fp8	No data	—	100%	100%	100%	2.16s	12.5s	45 tps	205K	$0.300 / $1.20
MiniMax M2.1novita/fp8fp8	No data	—	99.69%	99.55%	99.64%	1.70s	3.79s	50 tps	205K	$0.300 / $1.20
MiniMax M2.5novita/fp8fp8	No data	—	99.60%	99.35%	99.68%	1.10s	2.73s	75 tps	205K	$0.300 / $1.20
MiniMax M3novita/fp8fp8	No data	—	99.67%	99.55%	99.62%	1.57s	12.0s	70 tps	1.0M	$0.300 / $1.20
Kimi K2.7 Codenovita/int4int4	No data	—	99.92%	99.93%	99.91%	2.00s	22.8s	83 tps	262K	$0.912 / $3.84
Qwen3 235B A22B Thinking 2507novita/fp8fp8	No data	—	100%	99.21%	97.97%	1.11s	4.22s	56 tps	131K	$0.300 / $3.00
Qwen3 Coder 480B A35Bnovita/fp8fp8	No data	—	72.79%	63.29%	84.42%	1.44s	6.35s	41 tps	262K	$0.380 / $1.55
Qwen3 VL 235B A22B Instructnovita/bf16bf16	Degraded	—	97.39%	96.06%	95.77%	1.71s	14.2s	40 tps	131K	$0.300 / $1.50
Qwen3 VL 235B A22B Thinkingnovita/bf16bf16	No data	—	99.65%	95.49%	99.07%	853ms	1.54s	48 tps	131K	$0.980 / $3.95
Qwen3.5 397B A17Bnovita	No data	—	95.91%	97.78%	98.70%	1.00s	10.0s	65 tps	262K	$0.600 / $3.60
Llama 3.1 Euryale 70B v2.2novita/fp8fp8	No data	—	99.36%	100%	96.45%	549ms	3.03s	37 tps	8K	$1.45 / $1.45
Hy3novita	No data	—	92.02%	98.95%	99.67%	3.76s	18.6s	73 tps	262K	$0.140 / $0.580
Hy4 previewnovita/fp8fp8	Degraded	—	80.63%	95.06%	96.91%	4.44s	9.68s	75 tps	1.0M	$0.834 / $2.50
GLM 4.5Vnovita/fp8fp8	No data	—	98.44%	98.35%	97.23%	3.23s	9.41s	32 tps	66K	$0.600 / $1.80
GLM 5.1novita/fp8fp8	No data	—	99.53%	98.90%	99.35%	2.31s	6.96s	32 tps	205K	$1.38 / $4.40

Apodex 1.1 Mini (free)100%
Healthy24h 99.99%
7d
99.98%
30d
99.98%
p50
1.43s
p99
6.09s
Throughput
116 tps
Context
262K
$/Mtok
free / free
novita/bf16bf16
R1100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.18s
p99
5.23s
Throughput
20 tps
Context
64K
$/Mtok
$0.700 / $2.50
novita/fp8fp8
R1 0528100%
Healthy24h 99.89%
7d
99.87%
30d
99.82%
p50
1.30s
p99
5.53s
Throughput
20 tps
Context
164K
$/Mtok
$0.700 / $2.50
novita/fp8fp8
DeepSeek V4 Flash 0731100%
Healthy24h 99.99%
7d
99.99%
30d
99.98%
p50
1.28s
p99
5.57s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.409 / $1.23
novita/fp8fp8
DeepSeek V4 Flash Vision Exp100%
Healthy24h 99.97%
7d
98.99%
30d
99.41%
p50
1.41s
p99
4.79s
Throughput
132 tps
Context
1.0M
$/Mtok
$0.440 / $1.32
novita
DeepSeek V4 Pro 0423100%
Healthy24h 99.97%
7d
99.94%
30d
99.91%
p50
2.48s
p99
13.7s
Throughput
58 tps
Context
1.0M
$/Mtok
$1.60 / $3.20
novita/fp8fp8
DeepSeek V4 Pro 0813100%
Healthy24h 99.97%
7d
99.97%
30d
99.92%
p50
1.76s
p99
4.67s
Throughput
75 tps
Context
1.0M
$/Mtok
$0.990 / $2.97
novita/fp8fp8
DeepSeek V4.1 Flash100%
Healthy24h 99.90%
7d
99.81%
30d
99.53%
p50
1.84s
p99
22.6s
Throughput
70 tps
Context
1.0M
$/Mtok
$0.240 / $0.960
novita/fp8fp8
Gemma 3 27B100%
Healthy24h 96.53%
7d
96.15%
30d
94.13%
p50
1.49s
p99
4.90s
Throughput
26 tps
Context
98K
$/Mtok
$0.119 / $0.200
novita/bf16bf16
Ling 3.0 Flash100%
Healthy24h 100%
7d
100%
30d
99.95%
p50
1.09s
p99
2.33s
Throughput
186 tps
Context
262K
$/Mtok
$0.021 / $0.063
novita
Ling 3.0 Flash Sante (free)100%
Healthy24h 100%
7d
100%
30d
99.97%
p50
1.15s
p99
8.32s
Throughput
161 tps
Context
262K
$/Mtok
free / free
novita
Ling 3.1 Flash100%
Healthy24h 100%
7d
100%
30d
100%
p50
2.44s
p99
230s
Throughput
60 tps
Context
262K
$/Mtok
free / free
novita
Llama 4 Scout100%
Healthy24h 99.90%
7d
99.92%
30d
99.64%
p50
741ms
p99
2.51s
Throughput
27 tps
Context
131K
$/Mtok
$0.180 / $0.590
novita/bf16bf16
WizardLM-2 8x22B100%
Healthy24h 99.99%
7d
99.99%
30d
100%
p50
1.79s
p99
7.05s
Throughput
16 tps
Context
66K
$/Mtok
$0.620 / $0.620
novita/bf16bf16
MiniMax M2.7100%
Healthy24h 99.50%
7d
99.56%
30d
99.53%
p50
1.65s
p99
4.75s
Throughput
49 tps
Context
205K
$/Mtok
$0.270 / $1.08
novita/fp8fp8
Mistral Nemo100%
Down24h 78.16%
7d
81.08%
30d
80.68%
p50
550ms
p99
28.4s
Throughput
68 tps
Context
60K
$/Mtok
$0.040 / $0.170
novita/fp8fp8
Kimi K2 0711100%
Healthy24h 100%
7d
100%
30d
99.99%
p50
794ms
p99
34.9s
Throughput
45 tps
Context
131K
$/Mtok
$0.570 / $2.30
novita/fp8fp8
Kimi K2 0905100%
Healthy24h 100%
7d
100%
30d
100%
p50
725ms
p99
6.94s
Throughput
46 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/fp8fp8
Kimi K2 Thinking100%
Healthy24h 99.93%
7d
99.78%
30d
99.59%
p50
1.81s
p99
13.5s
Throughput
47 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/bf16bf16
Kimi K2.6100%
Healthy24h 99.95%
7d
99.80%
30d
99.27%
p50
1.60s
p99
41.4s
Throughput
48 tps
Context
262K
$/Mtok
$0.800 / $3.40
novita
Nemotron 3 Nano 30B A3B100%
Healthy24h 99.98%
7d
99.69%
30d
99.85%
p50
455ms
p99
6.71s
Throughput
255 tps
Context
262K
$/Mtok
$0.050 / $0.200
novita/fp4fp4
gpt-oss-20b100%
Healthy24h 99.94%
7d
99.77%
30d
99.77%
p50
736ms
p99
2.98s
Throughput
102 tps
Context
131K
$/Mtok
$0.040 / $0.150
novita/fp4fp4
Qwen2.5 72B Instruct100%
Healthy24h 99.48%
7d
95.85%
30d
95.44%
p50
697ms
p99
3.74s
Throughput
25 tps
Context
32K
$/Mtok
$0.380 / $0.400
novita/bf16bf16
Qwen3 235B A22B Instruct 2507100%
Healthy24h 95.55%
7d
96.56%
30d
97.88%
p50
733ms
p99
94.5s
Throughput
53 tps
Context
131K
$/Mtok
$0.090 / $0.580
novita/fp8fp8
Qwen3 Coder 30B A3B Instruct100%
Healthy24h 97.39%
7d
98.53%
30d
97.81%
p50
931ms
p99
3.18s
Throughput
51 tps
Context
160K
$/Mtok
$0.070 / $0.270
novita/fp8fp8
Qwen3 Coder Next100%
Healthy24h 99.64%
7d
99.66%
30d
99.63%
p50
1.84s
p99
9.59s
Throughput
54 tps
Context
262K
$/Mtok
$0.200 / $1.50
novita/fp8fp8
Qwen3.5-122B-A10B100%
Healthy24h 99.57%
7d
99.05%
30d
99.59%
p50
578ms
p99
3.28s
Throughput
108 tps
Context
262K
$/Mtok
$0.400 / $3.20
novita/bf16bf16
Qwen3.5-27B100%
Healthy24h 99.97%
7d
99.96%
30d
99.73%
p50
979ms
p99
5.10s
Throughput
53 tps
Context
262K
$/Mtok
$0.300 / $2.40
novita/bf16bf16
Qwen3.8 2.4T A95B100%
Healthy24h 99.94%
7d
99.87%
30d
99.90%
p50
2.89s
p99
22.6s
Throughput
39 tps
Context
1.0M
$/Mtok
$2.00 / $6.00
novita
Qwen3.8 27B100%
Healthy24h 99.96%
7d
99.81%
30d
99.77%
p50
6.79s
p99
55.7s
Throughput
49 tps
Context
1.0M
$/Mtok
$0.420 / $3.00
novita
Llama 3 8B Lunaris100%
Healthy24h 99.98%
7d
99.98%
30d
99.91%
p50
320ms
p99
1.61s
Throughput
74 tps
Context
8K
$/Mtok
$0.050 / $0.050
novita/bf16bf16
Step 3.7 Flash100%
Healthy24h 99.83%
7d
99.74%
30d
99.30%
p50
3.87s
p99
13.8s
Throughput
90 tps
Context
262K
$/Mtok
$0.200 / $1.15
novita/fp8fp8
MiMo-V2.5100%
Healthy24h 97.80%
7d
96.29%
30d
96.71%
p50
2.08s
p99
21.9s
Throughput
47 tps
Context
1.0M
$/Mtok
$0.168 / $0.336
novita/fp8fp8
GLM 4.5 Air100%
Healthy24h 99.87%
7d
99.84%
30d
99.74%
p50
831ms
p99
11.9s
Throughput
63 tps
Context
131K
$/Mtok
$0.130 / $0.850
novita/bf16bf16
GLM 4.6V100%
Healthy24h 99.86%
7d
99.47%
30d
97.80%
p50
1.48s
p99
7.90s
Throughput
52 tps
Context
131K
$/Mtok
$0.300 / $0.900
novita/bf16bf16
GLM 4.7100%
Healthy24h 99.58%
7d
99.66%
30d
96.85%
p50
4.16s
p99
11.3s
Throughput
27 tps
Context
205K
$/Mtok
$0.540 / $1.98
novita/fp8fp8
GLM 5100%
Healthy24h 100%
7d
100%
30d
99.97%
p50
1.35s
p99
9.66s
Throughput
44 tps
Context
203K
$/Mtok
$1.00 / $3.20
novita/fp8fp8
GLM 5.2100%
Healthy24h 99.84%
7d
99.73%
30d
99.89%
p50
1.53s
p99
8.53s
Throughput
53 tps
Context
1.0M
$/Mtok
$0.650 / $2.04
novita/fp8fp8
DeepSeek V4 Flash 042399.97%
Healthy24h 99.96%
7d
99.95%
30d
99.93%
p50
1.33s
p99
6.91s
Throughput
62 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
Ling 3.0 Flash VL99.97%
Healthy24h 99.95%
7d
99.77%
30d
99.77%
p50
906ms
p99
9.62s
Throughput
119 tps
Context
262K
$/Mtok
$0.021 / $0.062
novita/bf16bf16
Gemma 4 31B99.95%
Healthy24h 91.81%
7d
82.51%
30d
88.92%
p50
707ms
p99
21.1s
Throughput
18 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
GLM 5.3 Flash99.92%
Healthy24h 98.76%
7d
99.06%
30d
98.72%
p50
1.72s
p99
12.5s
Throughput
46 tps
Context
1.0M
$/Mtok
$0.084 / $0.280
novita/fp8fp8
Llama 3.1 8B Instruct99.88%
Healthy24h 99.77%
7d
99.26%
30d
98.57%
p50
498ms
p99
3.10s
Throughput
85 tps
Context
16K
$/Mtok
$0.020 / $0.050
novita/fp8fp8
Gemma 4 26B A4B 99.87%
Healthy24h 99.90%
7d
99.54%
30d
99.49%
p50
869ms
p99
7.84s
Throughput
76 tps
Context
262K
$/Mtok
$0.130 / $0.400
novita/bf16bf16
Llama 3.3 70B Instruct99.84%
Healthy24h 95.79%
7d
92.96%
30d
97.42%
p50
1.24s
p99
3.22s
Throughput
33 tps
Context
12K
$/Mtok
$0.135 / $0.400
novita/bf16bf16
Qwen3 VL 30B A3B Instruct99.47%
Healthy24h 99.16%
7d
98.82%
30d
97.66%
p50
776ms
p99
5.49s
Throughput
98 tps
Context
131K
$/Mtok
$0.200 / $0.700
novita/bf16bf16
MiMo-V2.6-Pro99.28%
Healthy24h 99.61%
7d
99.59%
30d
99.59%
p50
4.35s
p99
45.4s
Throughput
35 tps
Context
1.0M
$/Mtok
$0.435 / $0.870
novita/fp8fp8
Llama 4 Maverick99.27%
Healthy24h 99.07%
7d
98.92%
30d
99.39%
p50
781ms
p99
6.16s
Throughput
23 tps
Context
1.0M
$/Mtok
$0.270 / $0.850
novita/fp8fp8
GLM 5.399.20%
Healthy24h 99.08%
7d
99.83%
30d
99.57%
p50
2.71s
p99
82.3s
Throughput
25 tps
Context
1.0M
$/Mtok
$0.420 / $1.32
novita/fp8fp8
GLM 4.698.89%
Healthy24h 99.84%
7d
98.83%
30d
96.99%
p50
4.31s
p99
9.91s
Throughput
27 tps
Context
205K
$/Mtok
$0.550 / $2.20
novita/bf16bf16
Kimi K2.598.53%
Healthy24h 98.59%
7d
98.35%
30d
96.93%
p50
1.42s
p99
13.4s
Throughput
46 tps
Context
262K
$/Mtok
$0.570 / $2.85
novita
MiMo-V2.5-Pro98.48%
Healthy24h 98.81%
7d
97.21%
30d
95.58%
p50
2.65s
p99
48.9s
Throughput
41 tps
Context
1.0M
$/Mtok
$0.480 / $0.960
novita
gpt-oss-120b96.62%
Healthy24h 98.82%
7d
98.97%
30d
92.00%
p50
847ms
p99
18.6s
Throughput
69 tps
Context
131K
$/Mtok
$0.050 / $0.250
novita/fp4fp4
MiMo-V2.6-Flash96.39%
Healthy24h 96.82%
7d
96.20%
30d
96.20%
p50
2.91s
p99
27.6s
Throughput
30 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
Qwen3 Next 80B A3B Instruct91.24%
Degraded24h 85.37%
7d
88.89%
30d
93.46%
p50
1.48s
p99
61.8s
Throughput
85 tps
Context
131K
$/Mtok
$0.150 / $1.50
novita/bf16bf16
GLM 4.7 Flash70.26%
Down24h 65.95%
7d
67.16%
30d
67.74%
p50
847ms
p99
27.2s
Throughput
68 tps
Context
200K
$/Mtok
$0.070 / $0.400
novita/bf16bf16
ERNIE 4.5 VL 424B A47B —
No data24h 100%
7d
100%
30d
100%
p50
1.83s
p99
13.7s
Throughput
25 tps
Context
123K
$/Mtok
$0.420 / $1.25
novita/fp16fp16
Ling 3.0 Flash Fin—
No data24h 100%
7d
99.98%
30d
99.98%
p50
914ms
p99
12.2s
Throughput
141 tps
Context
262K
$/Mtok
$0.042 / $0.123
novita
MiniMax M1—
No data24h 100%
7d
100%
30d
100%
p50
1.22s
p99
3.00s
Throughput
54 tps
Context
1.0M
$/Mtok
$0.550 / $2.20
novita/bf16bf16
MiniMax M2—
No data24h 100%
7d
100%
30d
100%
p50
2.16s
p99
12.5s
Throughput
45 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.1—
No data24h 99.69%
7d
99.55%
30d
99.64%
p50
1.70s
p99
3.79s
Throughput
50 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.5—
No data24h 99.60%
7d
99.35%
30d
99.68%
p50
1.10s
p99
2.73s
Throughput
75 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M3—
No data24h 99.67%
7d
99.55%
30d
99.62%
p50
1.57s
p99
12.0s
Throughput
70 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
novita/fp8fp8
Kimi K2.7 Code—
No data24h 99.92%
7d
99.93%
30d
99.91%
p50
2.00s
p99
22.8s
Throughput
83 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
Qwen3 235B A22B Thinking 2507—
No data24h 100%
7d
99.21%
30d
97.97%
p50
1.11s
p99
4.22s
Throughput
56 tps
Context
131K
$/Mtok
$0.300 / $3.00
novita/fp8fp8
Qwen3 Coder 480B A35B—
No data24h 72.79%
7d
63.29%
30d
84.42%
p50
1.44s
p99
6.35s
Throughput
41 tps
Context
262K
$/Mtok
$0.380 / $1.55
novita/fp8fp8
Qwen3 VL 235B A22B Instruct—
Degraded24h 97.39%
7d
96.06%
30d
95.77%
p50
1.71s
p99
14.2s
Throughput
40 tps
Context
131K
$/Mtok
$0.300 / $1.50
novita/bf16bf16
Qwen3 VL 235B A22B Thinking—
No data24h 99.65%
7d
95.49%
30d
99.07%
p50
853ms
p99
1.54s
Throughput
48 tps
Context
131K
$/Mtok
$0.980 / $3.95
novita/bf16bf16
Qwen3.5 397B A17B—
No data24h 95.91%
7d
97.78%
30d
98.70%
p50
1.00s
p99
10.0s
Throughput
65 tps
Context
262K
$/Mtok
$0.600 / $3.60
novita
Llama 3.1 Euryale 70B v2.2—
No data24h 99.36%
7d
100%
30d
96.45%
p50
549ms
p99
3.03s
Throughput
37 tps
Context
8K
$/Mtok
$1.45 / $1.45
novita/fp8fp8
Hy3—
No data24h 92.02%
7d
98.95%
30d
99.67%
p50
3.76s
p99
18.6s
Throughput
73 tps
Context
262K
$/Mtok
$0.140 / $0.580
novita
Hy4 preview—
Degraded24h 80.63%
7d
95.06%
30d
96.91%
p50
4.44s
p99
9.68s
Throughput
75 tps
Context
1.0M
$/Mtok
$0.834 / $2.50
novita/fp8fp8
GLM 4.5V—
No data24h 98.44%
7d
98.35%
30d
97.23%
p50
3.23s
p99
9.41s
Throughput
32 tps
Context
66K
$/Mtok
$0.600 / $1.80
novita/fp8fp8
GLM 5.1—
No data24h 99.53%
7d
98.90%
30d
99.35%
p50
2.31s
p99
6.96s
Throughput
32 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8