Novita

74 endpoints · 6 unhealthy · worst uptime 73.36%

	State
Apodex 1.1 Mini (free)novita/bf16bf16	Healthy	100%	99.99%	99.98%	99.98%	1.40s	6.24s	131 tps	262K	free / free
R1novita/fp8fp8	Healthy	100%	100%	100%	100%	1.12s	3.90s	20 tps	64K	$0.700 / $2.50
R1 0528novita/fp8fp8	Healthy	100%	99.89%	99.87%	99.82%	1.24s	11.2s	20 tps	164K	$0.700 / $2.50
DeepSeek V4 Flash 0731novita/fp8fp8	Healthy	100%	99.99%	99.99%	99.98%	1.25s	5.83s	61 tps	1.0M	$0.409 / $1.23
DeepSeek V4 Flash Vision Expnovita	Healthy	100%	99.97%	99.00%	99.41%	1.32s	4.11s	96 tps	1.0M	$0.440 / $1.32
DeepSeek V4 Pro 0423novita/fp8fp8	Healthy	100%	99.97%	99.94%	99.91%	2.31s	11.7s	58 tps	1.0M	$1.60 / $3.20
DeepSeek V4 Pro 0813novita/fp8fp8	Healthy	100%	99.97%	99.97%	99.92%	1.56s	6.39s	82 tps	1.0M	$0.990 / $2.97
DeepSeek V4.1 Flashnovita/fp8fp8	Healthy	100%	99.89%	99.81%	99.53%	1.68s	28.4s	76 tps	1.0M	$0.240 / $0.960
Gemma 4 26B A4B novita/bf16bf16	Healthy	100%	99.90%	99.54%	99.49%	835ms	10.7s	80 tps	262K	$0.130 / $0.400
Ling 3.0 Flashnovita	Healthy	100%	100%	100%	99.95%	1.03s	2.24s	183 tps	262K	$0.021 / $0.063
Ling 3.0 Flash Sante (free)novita	Healthy	100%	100%	100%	99.97%	1.17s	7.67s	157 tps	262K	free / free
Ling 3.1 Flashnovita	Healthy	100%	100%	100%	100%	2.36s	228s	66 tps	262K	free / free
Llama 3.3 70B Instructnovita/bf16bf16	Healthy	100%	96.13%	93.00%	97.42%	1.12s	3.89s	37 tps	12K	$0.135 / $0.400
Llama 4 Scoutnovita/bf16bf16	Healthy	100%	99.90%	99.92%	99.64%	745ms	2.27s	30 tps	131K	$0.180 / $0.590
WizardLM-2 8x22Bnovita/bf16bf16	Healthy	100%	99.99%	99.99%	100%	1.87s	9.01s	16 tps	66K	$0.620 / $0.620
MiniMax M2.7novita/fp8fp8	Healthy	100%	99.50%	99.56%	99.53%	1.65s	8.17s	50 tps	205K	$0.270 / $1.08
MiniMax M3novita/fp8fp8	Healthy	100%	99.69%	99.54%	99.62%	1.53s	34.6s	72 tps	1.0M	$0.300 / $1.20
Kimi K2 0711novita/fp8fp8	Healthy	100%	100%	100%	99.99%	917ms	18.0s	42 tps	131K	$0.570 / $2.30
Kimi K2 0905novita/fp8fp8	Healthy	100%	100%	100%	100%	698ms	3.07s	46 tps	262K	$0.600 / $2.50
Kimi K2.5novita	Healthy	100%	98.64%	98.35%	96.93%	1.38s	25.2s	47 tps	262K	$0.570 / $2.85
Kimi K2.6novita	Healthy	100%	99.95%	99.80%	99.27%	2.51s	17.8s	28 tps	262K	$0.800 / $3.40
Nemotron 3 Nano 30B A3Bnovita/fp4fp4	Healthy	100%	99.98%	99.70%	99.85%	377ms	5.56s	119 tps	262K	$0.050 / $0.200
gpt-oss-20bnovita/fp4fp4	Healthy	100%	99.94%	99.78%	99.77%	811ms	9.77s	57 tps	131K	$0.040 / $0.150
Qwen2.5 72B Instructnovita/bf16bf16	Healthy	100%	99.49%	95.87%	95.45%	765ms	4.65s	31 tps	32K	$0.380 / $0.400
Qwen3 Coder Nextnovita/fp8fp8	Healthy	100%	99.64%	99.66%	99.63%	1.76s	9.86s	89 tps	262K	$0.200 / $1.50
Qwen3.5-27Bnovita/bf16bf16	Healthy	100%	99.97%	99.96%	99.73%	945ms	5.59s	49 tps	262K	$0.300 / $2.40
Qwen3.8 2.4T A95Bnovita	Healthy	100%	99.97%	99.87%	99.90%	3.21s	22.3s	35 tps	1.0M	$2.00 / $6.00
Qwen3.8 27Bnovita	Healthy	100%	99.96%	99.81%	99.77%	8.87s	47.5s	50 tps	1.0M	$0.420 / $3.00
Llama 3 8B Lunarisnovita/bf16bf16	Healthy	100%	99.98%	99.98%	99.91%	317ms	1.52s	76 tps	8K	$0.050 / $0.050
Step 3.7 Flashnovita/fp8fp8	Healthy	100%	99.82%	99.75%	99.30%	5.45s	14.6s	55 tps	262K	$0.200 / $1.15
MiMo-V2.5-Pronovita	Healthy	100%	98.81%	97.22%	95.59%	2.14s	13.9s	40 tps	1.0M	$0.480 / $0.960
GLM 4.5 Airnovita/bf16bf16	Healthy	100%	99.89%	99.84%	99.74%	1.05s	8.53s	56 tps	131K	$0.130 / $0.850
GLM 4.6novita/bf16bf16	Healthy	100%	99.84%	98.84%	97.00%	4.23s	13.4s	25 tps	205K	$0.550 / $2.20
GLM 4.7novita/fp8fp8	Healthy	100%	99.58%	99.67%	96.85%	4.21s	8.00s	27 tps	205K	$0.540 / $1.98
GLM 5novita/fp8fp8	Healthy	100%	100%	100%	99.97%	1.22s	8.56s	47 tps	203K	$1.00 / $3.20
GLM 5.2novita/fp8fp8	Healthy	100%	99.84%	99.73%	99.89%	1.53s	5.04s	57 tps	1.0M	$0.650 / $2.04
DeepSeek V4 Flash 0423novita/fp8fp8	Healthy	99.99%	99.96%	99.95%	99.93%	1.33s	5.62s	67 tps	1.0M	$0.140 / $0.280
Llama 3.1 8B Instructnovita/fp8fp8	Healthy	99.97%	99.77%	99.26%	98.57%	488ms	2.59s	98 tps	16K	$0.020 / $0.050
Ling 3.0 Flash VLnovita/bf16bf16	Healthy	99.96%	99.95%	99.77%	99.77%	913ms	10.7s	143 tps	262K	$0.021 / $0.062
MiMo-V2.6-Pronovita/fp8fp8	Healthy	99.93%	99.62%	99.59%	99.59%	3.78s	35.7s	34 tps	1.0M	$0.435 / $0.870
GLM 5.3 Flashnovita/fp8fp8	Healthy	99.79%	98.77%	99.06%	98.72%	1.74s	12.9s	44 tps	1.0M	$0.084 / $0.280
Llama 4 Mavericknovita/fp8fp8	Healthy	99.66%	99.13%	98.93%	99.39%	716ms	7.08s	28 tps	1.0M	$0.270 / $0.850
Qwen3 VL 30B A3B Instructnovita/bf16bf16	Healthy	99.15%	99.14%	98.82%	97.66%	965ms	6.14s	62 tps	131K	$0.200 / $0.700
Qwen3 235B A22B Instruct 2507novita/fp8fp8	Healthy	98.89%	95.47%	96.57%	97.89%	749ms	10.1s	44 tps	131K	$0.090 / $0.580
MiMo-V2.5novita/fp8fp8	Healthy	98.76%	97.93%	96.31%	96.72%	2.07s	9.86s	47 tps	1.0M	$0.168 / $0.336
GLM 5.3novita/fp8fp8	Healthy	98.69%	98.94%	99.81%	99.57%	3.01s	84.9s	25 tps	1.0M	$0.420 / $1.32
MiMo-V2.6-Flashnovita/fp8fp8	Healthy	98.27%	96.74%	96.21%	96.21%	2.64s	26.6s	30 tps	1.0M	$0.140 / $0.280
Gemma 3 27Bnovita/bf16bf16	Healthy	98.19%	96.56%	96.17%	94.14%	1.35s	5.89s	28 tps	98K	$0.119 / $0.200
gpt-oss-120bnovita/fp4fp4	Degraded	93.75%	98.70%	98.95%	92.00%	788ms	19.4s	75 tps	131K	$0.050 / $0.250
Qwen3 VL 235B A22B Instructnovita/bf16bf16	Degraded	91.80%	97.33%	96.02%	95.76%	1.71s	21.2s	35 tps	131K	$0.300 / $1.50
Qwen3 Next 80B A3B Instructnovita/bf16bf16	Down	91.59%	84.89%	88.79%	93.42%	1.65s	73.3s	19 tps	131K	$0.150 / $1.50
Gemma 4 31Bnovita/bf16bf16	Down	88.07%	92.13%	82.61%	88.94%	2.63s	150s	13 tps	262K	$0.140 / $0.400
GLM 4.7 Flashnovita/bf16bf16	Down	82.48%	65.41%	67.18%	67.74%	863ms	27.1s	66 tps	200K	$0.070 / $0.400
Mistral Nemonovita/fp8fp8	Down	73.36%	78.02%	81.14%	80.70%	650ms	39.2s	72 tps	60K	$0.040 / $0.170
ERNIE 4.5 VL 424B A47B novita/fp16fp16	No data	—	100%	100%	100%	2.18s	7.87s	26 tps	123K	$0.420 / $1.25
Ling 3.0 Flash Finnovita	No data	—	100%	99.98%	99.98%	830ms	10.6s	146 tps	262K	$0.042 / $0.123
MiniMax M1novita/bf16bf16	No data	—	100%	100%	100%	1.02s	2.59s	44 tps	1.0M	$0.550 / $2.20
MiniMax M2novita/fp8fp8	No data	—	100%	100%	100%	1.52s	1.95s	83 tps	205K	$0.300 / $1.20
MiniMax M2.1novita/fp8fp8	No data	—	99.69%	99.55%	99.64%	1.95s	14.2s	40 tps	205K	$0.300 / $1.20
MiniMax M2.5novita/fp8fp8	No data	—	99.60%	99.35%	99.68%	1.14s	3.41s	64 tps	205K	$0.300 / $1.20
Kimi K2 Thinkingnovita/bf16bf16	No data	—	99.93%	99.78%	99.59%	1.41s	8.04s	53 tps	262K	$0.600 / $2.50
Kimi K2.7 Codenovita/int4int4	No data	—	99.92%	99.93%	99.91%	1.68s	22.3s	88 tps	262K	$0.912 / $3.84
Qwen3 235B A22B Thinking 2507novita/fp8fp8	No data	—	100%	99.21%	97.97%	950ms	1.97s	80 tps	131K	$0.300 / $3.00
Qwen3 Coder 480B A35Bnovita/fp8fp8	No data	—	72.48%	63.52%	84.43%	1.56s	8.44s	48 tps	262K	$0.380 / $1.55
Qwen3 Coder 30B A3B Instructnovita/fp8fp8	No data	—	97.29%	98.53%	97.81%	893ms	2.20s	56 tps	160K	$0.070 / $0.270
Qwen3 VL 235B A22B Thinkingnovita/bf16bf16	No data	—	99.65%	95.49%	99.07%	892ms	92.6s	48 tps	131K	$0.980 / $3.95
Qwen3.5-122B-A10Bnovita/bf16bf16	No data	—	99.60%	99.06%	99.59%	917ms	9.24s	111 tps	262K	$0.400 / $3.20
Qwen3.5 397B A17Bnovita	No data	—	97.04%	97.78%	98.70%	1.01s	8.25s	67 tps	262K	$0.600 / $3.60
Llama 3.1 Euryale 70B v2.2novita/fp8fp8	No data	—	99.35%	100%	96.45%	450ms	2.36s	38 tps	8K	$1.45 / $1.45
Hy3novita	No data	—	92.58%	98.95%	99.67%	3.41s	12.8s	72 tps	262K	$0.140 / $0.580
Hy4 previewnovita/fp8fp8	No data	—	80.63%	95.08%	96.92%	4.57s	11.7s	51 tps	1.0M	$0.834 / $2.50
GLM 4.5Vnovita/fp8fp8	No data	—	98.35%	98.35%	97.23%	1.10s	6.85s	46 tps	66K	$0.600 / $1.80
GLM 4.6Vnovita/bf16bf16	No data	—	99.85%	99.48%	97.80%	1.24s	14.9s	41 tps	131K	$0.300 / $0.900
GLM 5.1novita/fp8fp8	No data	—	99.54%	98.91%	99.36%	4.10s	17.3s	28 tps	205K	$1.38 / $4.40

Apodex 1.1 Mini (free)100%
Healthy24h 99.99%
7d
99.98%
30d
99.98%
p50
1.40s
p99
6.24s
Throughput
131 tps
Context
262K
$/Mtok
free / free
novita/bf16bf16
R1100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.12s
p99
3.90s
Throughput
20 tps
Context
64K
$/Mtok
$0.700 / $2.50
novita/fp8fp8
R1 0528100%
Healthy24h 99.89%
7d
99.87%
30d
99.82%
p50
1.24s
p99
11.2s
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
1.25s
p99
5.83s
Throughput
61 tps
Context
1.0M
$/Mtok
$0.409 / $1.23
novita/fp8fp8
DeepSeek V4 Flash Vision Exp100%
Healthy24h 99.97%
7d
99.00%
30d
99.41%
p50
1.32s
p99
4.11s
Throughput
96 tps
Context
1.0M
$/Mtok
$0.440 / $1.32
novita
DeepSeek V4 Pro 0423100%
Healthy24h 99.97%
7d
99.94%
30d
99.91%
p50
2.31s
p99
11.7s
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
1.56s
p99
6.39s
Throughput
82 tps
Context
1.0M
$/Mtok
$0.990 / $2.97
novita/fp8fp8
DeepSeek V4.1 Flash100%
Healthy24h 99.89%
7d
99.81%
30d
99.53%
p50
1.68s
p99
28.4s
Throughput
76 tps
Context
1.0M
$/Mtok
$0.240 / $0.960
novita/fp8fp8
Gemma 4 26B A4B 100%
Healthy24h 99.90%
7d
99.54%
30d
99.49%
p50
835ms
p99
10.7s
Throughput
80 tps
Context
262K
$/Mtok
$0.130 / $0.400
novita/bf16bf16
Ling 3.0 Flash100%
Healthy24h 100%
7d
100%
30d
99.95%
p50
1.03s
p99
2.24s
Throughput
183 tps
Context
262K
$/Mtok
$0.021 / $0.063
novita
Ling 3.0 Flash Sante (free)100%
Healthy24h 100%
7d
100%
30d
99.97%
p50
1.17s
p99
7.67s
Throughput
157 tps
Context
262K
$/Mtok
free / free
novita
Ling 3.1 Flash100%
Healthy24h 100%
7d
100%
30d
100%
p50
2.36s
p99
228s
Throughput
66 tps
Context
262K
$/Mtok
free / free
novita
Llama 3.3 70B Instruct100%
Healthy24h 96.13%
7d
93.00%
30d
97.42%
p50
1.12s
p99
3.89s
Throughput
37 tps
Context
12K
$/Mtok
$0.135 / $0.400
novita/bf16bf16
Llama 4 Scout100%
Healthy24h 99.90%
7d
99.92%
30d
99.64%
p50
745ms
p99
2.27s
Throughput
30 tps
Context
131K
$/Mtok
$0.180 / $0.590
novita/bf16bf16
WizardLM-2 8x22B100%
Healthy24h 99.99%
7d
99.99%
30d
100%
p50
1.87s
p99
9.01s
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
8.17s
Throughput
50 tps
Context
205K
$/Mtok
$0.270 / $1.08
novita/fp8fp8
MiniMax M3100%
Healthy24h 99.69%
7d
99.54%
30d
99.62%
p50
1.53s
p99
34.6s
Throughput
72 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
novita/fp8fp8
Kimi K2 0711100%
Healthy24h 100%
7d
100%
30d
99.99%
p50
917ms
p99
18.0s
Throughput
42 tps
Context
131K
$/Mtok
$0.570 / $2.30
novita/fp8fp8
Kimi K2 0905100%
Healthy24h 100%
7d
100%
30d
100%
p50
698ms
p99
3.07s
Throughput
46 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/fp8fp8
Kimi K2.5100%
Healthy24h 98.64%
7d
98.35%
30d
96.93%
p50
1.38s
p99
25.2s
Throughput
47 tps
Context
262K
$/Mtok
$0.570 / $2.85
novita
Kimi K2.6100%
Healthy24h 99.95%
7d
99.80%
30d
99.27%
p50
2.51s
p99
17.8s
Throughput
28 tps
Context
262K
$/Mtok
$0.800 / $3.40
novita
Nemotron 3 Nano 30B A3B100%
Healthy24h 99.98%
7d
99.70%
30d
99.85%
p50
377ms
p99
5.56s
Throughput
119 tps
Context
262K
$/Mtok
$0.050 / $0.200
novita/fp4fp4
gpt-oss-20b100%
Healthy24h 99.94%
7d
99.78%
30d
99.77%
p50
811ms
p99
9.77s
Throughput
57 tps
Context
131K
$/Mtok
$0.040 / $0.150
novita/fp4fp4
Qwen2.5 72B Instruct100%
Healthy24h 99.49%
7d
95.87%
30d
95.45%
p50
765ms
p99
4.65s
Throughput
31 tps
Context
32K
$/Mtok
$0.380 / $0.400
novita/bf16bf16
Qwen3 Coder Next100%
Healthy24h 99.64%
7d
99.66%
30d
99.63%
p50
1.76s
p99
9.86s
Throughput
89 tps
Context
262K
$/Mtok
$0.200 / $1.50
novita/fp8fp8
Qwen3.5-27B100%
Healthy24h 99.97%
7d
99.96%
30d
99.73%
p50
945ms
p99
5.59s
Throughput
49 tps
Context
262K
$/Mtok
$0.300 / $2.40
novita/bf16bf16
Qwen3.8 2.4T A95B100%
Healthy24h 99.97%
7d
99.87%
30d
99.90%
p50
3.21s
p99
22.3s
Throughput
35 tps
Context
1.0M
$/Mtok
$2.00 / $6.00
novita
Qwen3.8 27B100%
Healthy24h 99.96%
7d
99.81%
30d
99.77%
p50
8.87s
p99
47.5s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.420 / $3.00
novita
Llama 3 8B Lunaris100%
Healthy24h 99.98%
7d
99.98%
30d
99.91%
p50
317ms
p99
1.52s
Throughput
76 tps
Context
8K
$/Mtok
$0.050 / $0.050
novita/bf16bf16
Step 3.7 Flash100%
Healthy24h 99.82%
7d
99.75%
30d
99.30%
p50
5.45s
p99
14.6s
Throughput
55 tps
Context
262K
$/Mtok
$0.200 / $1.15
novita/fp8fp8
MiMo-V2.5-Pro100%
Healthy24h 98.81%
7d
97.22%
30d
95.59%
p50
2.14s
p99
13.9s
Throughput
40 tps
Context
1.0M
$/Mtok
$0.480 / $0.960
novita
GLM 4.5 Air100%
Healthy24h 99.89%
7d
99.84%
30d
99.74%
p50
1.05s
p99
8.53s
Throughput
56 tps
Context
131K
$/Mtok
$0.130 / $0.850
novita/bf16bf16
GLM 4.6100%
Healthy24h 99.84%
7d
98.84%
30d
97.00%
p50
4.23s
p99
13.4s
Throughput
25 tps
Context
205K
$/Mtok
$0.550 / $2.20
novita/bf16bf16
GLM 4.7100%
Healthy24h 99.58%
7d
99.67%
30d
96.85%
p50
4.21s
p99
8.00s
Throughput
27 tps
Context
205K
$/Mtok
$0.540 / $1.98
novita/fp8fp8
GLM 5100%
Healthy24h 100%
7d
100%
30d
99.97%
p50
1.22s
p99
8.56s
Throughput
47 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
5.04s
Throughput
57 tps
Context
1.0M
$/Mtok
$0.650 / $2.04
novita/fp8fp8
DeepSeek V4 Flash 042399.99%
Healthy24h 99.96%
7d
99.95%
30d
99.93%
p50
1.33s
p99
5.62s
Throughput
67 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
Llama 3.1 8B Instruct99.97%
Healthy24h 99.77%
7d
99.26%
30d
98.57%
p50
488ms
p99
2.59s
Throughput
98 tps
Context
16K
$/Mtok
$0.020 / $0.050
novita/fp8fp8
Ling 3.0 Flash VL99.96%
Healthy24h 99.95%
7d
99.77%
30d
99.77%
p50
913ms
p99
10.7s
Throughput
143 tps
Context
262K
$/Mtok
$0.021 / $0.062
novita/bf16bf16
MiMo-V2.6-Pro99.93%
Healthy24h 99.62%
7d
99.59%
30d
99.59%
p50
3.78s
p99
35.7s
Throughput
34 tps
Context
1.0M
$/Mtok
$0.435 / $0.870
novita/fp8fp8
GLM 5.3 Flash99.79%
Healthy24h 98.77%
7d
99.06%
30d
98.72%
p50
1.74s
p99
12.9s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.084 / $0.280
novita/fp8fp8
Llama 4 Maverick99.66%
Healthy24h 99.13%
7d
98.93%
30d
99.39%
p50
716ms
p99
7.08s
Throughput
28 tps
Context
1.0M
$/Mtok
$0.270 / $0.850
novita/fp8fp8
Qwen3 VL 30B A3B Instruct99.15%
Healthy24h 99.14%
7d
98.82%
30d
97.66%
p50
965ms
p99
6.14s
Throughput
62 tps
Context
131K
$/Mtok
$0.200 / $0.700
novita/bf16bf16
Qwen3 235B A22B Instruct 250798.89%
Healthy24h 95.47%
7d
96.57%
30d
97.89%
p50
749ms
p99
10.1s
Throughput
44 tps
Context
131K
$/Mtok
$0.090 / $0.580
novita/fp8fp8
MiMo-V2.598.76%
Healthy24h 97.93%
7d
96.31%
30d
96.72%
p50
2.07s
p99
9.86s
Throughput
47 tps
Context
1.0M
$/Mtok
$0.168 / $0.336
novita/fp8fp8
GLM 5.398.69%
Healthy24h 98.94%
7d
99.81%
30d
99.57%
p50
3.01s
p99
84.9s
Throughput
25 tps
Context
1.0M
$/Mtok
$0.420 / $1.32
novita/fp8fp8
MiMo-V2.6-Flash98.27%
Healthy24h 96.74%
7d
96.21%
30d
96.21%
p50
2.64s
p99
26.6s
Throughput
30 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
Gemma 3 27B98.19%
Healthy24h 96.56%
7d
96.17%
30d
94.14%
p50
1.35s
p99
5.89s
Throughput
28 tps
Context
98K
$/Mtok
$0.119 / $0.200
novita/bf16bf16
gpt-oss-120b93.75%
Degraded24h 98.70%
7d
98.95%
30d
92.00%
p50
788ms
p99
19.4s
Throughput
75 tps
Context
131K
$/Mtok
$0.050 / $0.250
novita/fp4fp4
Qwen3 VL 235B A22B Instruct91.80%
Degraded24h 97.33%
7d
96.02%
30d
95.76%
p50
1.71s
p99
21.2s
Throughput
35 tps
Context
131K
$/Mtok
$0.300 / $1.50
novita/bf16bf16
Qwen3 Next 80B A3B Instruct91.59%
Down24h 84.89%
7d
88.79%
30d
93.42%
p50
1.65s
p99
73.3s
Throughput
19 tps
Context
131K
$/Mtok
$0.150 / $1.50
novita/bf16bf16
Gemma 4 31B88.07%
Down24h 92.13%
7d
82.61%
30d
88.94%
p50
2.63s
p99
150s
Throughput
13 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
GLM 4.7 Flash82.48%
Down24h 65.41%
7d
67.18%
30d
67.74%
p50
863ms
p99
27.1s
Throughput
66 tps
Context
200K
$/Mtok
$0.070 / $0.400
novita/bf16bf16
Mistral Nemo73.36%
Down24h 78.02%
7d
81.14%
30d
80.70%
p50
650ms
p99
39.2s
Throughput
72 tps
Context
60K
$/Mtok
$0.040 / $0.170
novita/fp8fp8
ERNIE 4.5 VL 424B A47B —
No data24h 100%
7d
100%
30d
100%
p50
2.18s
p99
7.87s
Throughput
26 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
830ms
p99
10.6s
Throughput
146 tps
Context
262K
$/Mtok
$0.042 / $0.123
novita
MiniMax M1—
No data24h 100%
7d
100%
30d
100%
p50
1.02s
p99
2.59s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.550 / $2.20
novita/bf16bf16
MiniMax M2—
No data24h 100%
7d
100%
30d
100%
p50
1.52s
p99
1.95s
Throughput
83 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.1—
No data24h 99.69%
7d
99.55%
30d
99.64%
p50
1.95s
p99
14.2s
Throughput
40 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.5—
No data24h 99.60%
7d
99.35%
30d
99.68%
p50
1.14s
p99
3.41s
Throughput
64 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
Kimi K2 Thinking—
No data24h 99.93%
7d
99.78%
30d
99.59%
p50
1.41s
p99
8.04s
Throughput
53 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/bf16bf16
Kimi K2.7 Code—
No data24h 99.92%
7d
99.93%
30d
99.91%
p50
1.68s
p99
22.3s
Throughput
88 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
950ms
p99
1.97s
Throughput
80 tps
Context
131K
$/Mtok
$0.300 / $3.00
novita/fp8fp8
Qwen3 Coder 480B A35B—
No data24h 72.48%
7d
63.52%
30d
84.43%
p50
1.56s
p99
8.44s
Throughput
48 tps
Context
262K
$/Mtok
$0.380 / $1.55
novita/fp8fp8
Qwen3 Coder 30B A3B Instruct—
No data24h 97.29%
7d
98.53%
30d
97.81%
p50
893ms
p99
2.20s
Throughput
56 tps
Context
160K
$/Mtok
$0.070 / $0.270
novita/fp8fp8
Qwen3 VL 235B A22B Thinking—
No data24h 99.65%
7d
95.49%
30d
99.07%
p50
892ms
p99
92.6s
Throughput
48 tps
Context
131K
$/Mtok
$0.980 / $3.95
novita/bf16bf16
Qwen3.5-122B-A10B—
No data24h 99.60%
7d
99.06%
30d
99.59%
p50
917ms
p99
9.24s
Throughput
111 tps
Context
262K
$/Mtok
$0.400 / $3.20
novita/bf16bf16
Qwen3.5 397B A17B—
No data24h 97.04%
7d
97.78%
30d
98.70%
p50
1.01s
p99
8.25s
Throughput
67 tps
Context
262K
$/Mtok
$0.600 / $3.60
novita
Llama 3.1 Euryale 70B v2.2—
No data24h 99.35%
7d
100%
30d
96.45%
p50
450ms
p99
2.36s
Throughput
38 tps
Context
8K
$/Mtok
$1.45 / $1.45
novita/fp8fp8
Hy3—
No data24h 92.58%
7d
98.95%
30d
99.67%
p50
3.41s
p99
12.8s
Throughput
72 tps
Context
262K
$/Mtok
$0.140 / $0.580
novita
Hy4 preview—
No data24h 80.63%
7d
95.08%
30d
96.92%
p50
4.57s
p99
11.7s
Throughput
51 tps
Context
1.0M
$/Mtok
$0.834 / $2.50
novita/fp8fp8
GLM 4.5V—
No data24h 98.35%
7d
98.35%
30d
97.23%
p50
1.10s
p99
6.85s
Throughput
46 tps
Context
66K
$/Mtok
$0.600 / $1.80
novita/fp8fp8
GLM 4.6V—
No data24h 99.85%
7d
99.48%
30d
97.80%
p50
1.24s
p99
14.9s
Throughput
41 tps
Context
131K
$/Mtok
$0.300 / $0.900
novita/bf16bf16
GLM 5.1—
No data24h 99.54%
7d
98.91%
30d
99.36%
p50
4.10s
p99
17.3s
Throughput
28 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8