Novita

71 endpoints · 10 unhealthy · worst uptime 58.98%

	State
DeepSeek V3.1novita/fp8fp8	Healthy	100%	99.99%	1.80s	7.78s	22 tps	131K	$0.270 / $1.00
R1novita/fp8fp8	Healthy	100%	100%	1.02s	14.9s	21 tps	64K	$0.700 / $2.50
R1 Distill Llama 70Bnovita/bf16bf16	Healthy	100%	100%	699ms	9.12s	28 tps	8K	$0.800 / $0.800
DeepSeek V3.1 Terminusnovita/fp8fp8	Healthy	100%	100%	1.87s	10.9s	21 tps	131K	$0.270 / $1.00
DeepSeek V3.2novita/fp8fp8	Healthy	100%	99.98%	1.25s	5.20s	28 tps	164K	$0.269 / $0.400
DeepSeek V4 Pro 0813novita/fp8fp8	Healthy	100%	99.81%	1.34s	14.8s	63 tps	1.0M	$1.32 / $3.96
Ling-2.6-1Tnovita	Healthy	100%	100%	1.37s	6.75s	68 tps	262K	$0.075 / $0.625
Ling-2.6-flashnovita	Healthy	100%	99.99%	562ms	1.96s	84 tps	262K	$0.010 / $0.030
Ling-3.0-flashnovita/fast	Healthy	100%	99.98%	677ms	5.71s	421 tps	262K	$0.042 / $0.126
Ring-2.6-1Tnovita	Healthy	100%	100%	1.63s	15.4s	86 tps	262K	$0.075 / $0.625
Llama 4 Mavericknovita/fp8fp8	Healthy	100%	99.88%	525ms	1.75s	45 tps	1.0M	$0.270 / $0.850
Llama 4 Scoutnovita/bf16bf16	Healthy	100%	99.15%	622ms	2.09s	26 tps	131K	$0.180 / $0.590
WizardLM-2 8x22Bnovita/bf16bf16	Healthy	100%	100%	51.2s	236s	1.0 tps	66K	$0.620 / $0.620
MiniMax M2.1novita/fp8fp8	Healthy	100%	99.82%	1.82s	5.68s	33 tps	205K	$0.300 / $1.20
Kimi K2 0711novita/fp8fp8	Healthy	100%	100%	732ms	22.7s	3.0 tps	131K	$0.570 / $2.30
Kimi K2 0905novita/fp8fp8	Healthy	100%	100%	637ms	3.69s	21 tps	262K	$0.600 / $2.50
Kimi K2.5novita	Healthy	100%	98.28%	1.15s	8.20s	35 tps	262K	$0.570 / $2.85
Kimi K2.6novita	Healthy	100%	99.56%	2.01s	10.0s	40 tps	262K	$0.800 / $3.40
Kimi K2.7 Codenovita/int4int4	Healthy	100%	99.48%	1.81s	10.1s	38 tps	262K	$0.912 / $3.84
Nemotron 3 Nano 30B A3Bnovita/fp4fp4	Healthy	100%	99.93%	560ms	5.31s	157 tps	262K	$0.050 / $0.200
gpt-oss-20bnovita/fp4fp4	Healthy	100%	99.92%	595ms	11.1s	91 tps	131K	$0.040 / $0.150
Qwen3 Coder Nextnovita/fp8fp8	Healthy	100%	99.42%	1.50s	24.8s	61 tps	262K	$0.200 / $1.50
Qwen3 Next 80B A3B Instructnovita/bf16bf16	Healthy	100%	99.80%	593ms	2.38s	28 tps	131K	$0.150 / $1.50
Qwen3.5-122B-A10Bnovita/bf16bf16	Healthy	100%	99.37%	991ms	4.50s	61 tps	262K	$0.400 / $3.20
Qwen3.5-27Bnovita/bf16bf16	Healthy	100%	99.85%	1.23s	6.95s	13 tps	262K	$0.300 / $2.40
Qwen3.5 397B A17Bnovita	Healthy	100%	97.73%	684ms	3.24s	3.0 tps	262K	$0.600 / $3.60
Llama 3 8B Lunarisnovita/bf16bf16	Healthy	100%	99.98%	304ms	899ms	73 tps	8K	$0.050 / $0.050
GLM 4.6Vnovita/bf16bf16	Healthy	100%	98.76%	3.03s	13.5s	15 tps	131K	$0.300 / $0.900
DeepSeek V4 Flash 0423novita/fp8fp8	Healthy	100%	99.85%	1.09s	5.80s	73 tps	1.0M	$0.140 / $0.280
Ling-3.0-flashnovita	Healthy	99.96%	99.98%	704ms	1.35s	53 tps	262K	$0.021 / $0.063
DeepSeek V4 Pro 0423novita/fp8fp8	Healthy	99.96%	99.38%	1.63s	7.34s	59 tps	1.0M	$1.60 / $3.20
DeepSeek V4 Flash 0731novita/fp8fp8	Healthy	99.86%	99.93%	1.20s	8.24s	66 tps	1.0M	$0.140 / $0.280
MiniMax M3novita/fp8fp8	Healthy	99.80%	99.62%	1.87s	14.1s	55 tps	1.0M	$0.300 / $1.20
Gemma 4 26B A4B novita/bf16bf16	Healthy	99.76%	93.35%	897ms	8.18s	22 tps	262K	$0.130 / $0.400
MiMo-V2.5novita/fp8fp8	Healthy	99.67%	98.05%	2.94s	20.5s	34 tps	1.0M	$0.168 / $0.336
MiMo-V2.5-Pronovita	Healthy	99.64%	97.45%	3.68s	33.9s	26 tps	1.0M	$0.480 / $0.960
DeepSeek V3.2 Expnovita/fp8fp8	Healthy	99.59%	99.40%	1.44s	7.18s	25 tps	164K	$0.270 / $0.410
Llama 3.1 8B Instructnovita/fp8fp8	Healthy	99.41%	99.78%	497ms	2.53s	59 tps	16K	$0.020 / $0.050
Qwen3 235B A22B Instruct 2507novita/fp8fp8	Healthy	99.35%	99.08%	696ms	11.0s	31 tps	131K	$0.090 / $0.580
GLM 4.5 Airnovita/bf16bf16	Healthy	99.31%	99.27%	659ms	10.1s	40 tps	131K	$0.130 / $0.850
Kimi K2 Thinkingnovita/bf16bf16	Healthy	99.05%	99.70%	898ms	7.95s	39 tps	262K	$0.600 / $2.50
GLM 4.6novita/bf16bf16	Healthy	98.89%	97.33%	1.16s	17.5s	46 tps	205K	$0.550 / $2.20
GLM 5.2novita/fp8fp8	Healthy	98.36%	99.57%	1.62s	27.0s	34 tps	1.0M	$0.741 / $2.33
DeepSeek V3 0324novita/fp8fp8	Degraded	98.10%	97.73%	1.31s	14.6s	31 tps	164K	$0.270 / $1.12
Step 3.7 Flashnovita/fp8fp8	Healthy	98.04%	97.70%	2.79s	12.2s	9.0 tps	262K	$0.200 / $1.15
Llama 3.3 70B Instructnovita/bf16bf16	Healthy	97.86%	96.40%	813ms	4.58s	27 tps	12K	$0.135 / $0.400
Gemma 4 31Bnovita/bf16bf16	Healthy	97.26%	82.69%	1.09s	9.03s	7.0 tps	262K	$0.140 / $0.400
Qwen3 VL 235B A22B Instructnovita/bf16bf16	Healthy	96.59%	94.76%	1.32s	13.2s	14 tps	131K	$0.300 / $1.50
Qwen3 VL 30B A3B Instructnovita/bf16bf16	Degraded	96.55%	95.73%	803ms	6.63s	18 tps	131K	$0.200 / $0.700
Hy3novita	Degraded	93.18%	99.25%	1.99s	8.30s	62 tps	262K	$0.140 / $0.580
gpt-oss-120bnovita/fp4fp4	Degraded	90.33%	95.82%	581ms	11.3s	61 tps	131K	$0.050 / $0.250
GLM 4.7novita/fp8fp8	Down	88.10%	93.80%	2.31s	38.6s	21 tps	205K	$0.540 / $1.98
DeepSeek V3novita/fp8fp8	Down	86.76%	97.27%	1.12s	8.27s	23 tps	64K	$0.400 / $1.30
GLM 4.7 Flashnovita/bf16bf16	Down	86.67%	80.72%	1.26s	75.6s	30 tps	200K	$0.070 / $0.400
Mistral Nemonovita/fp8fp8	Down	71.64%	54.06%	2.45s	57.1s	9.0 tps	60K	$0.040 / $0.170
Gemma 3 27Bnovita/bf16bf16	Down	58.98%	87.58%	901ms	64.7s	15 tps	98K	$0.119 / $0.200
ERNIE 4.5 VL 424B A47B novita/fp16fp16	No data	—	100%	1.25s	4.72s	21 tps	123K	$0.420 / $1.25
R1 0528novita/fp8fp8	No data	—	100%	889ms	2.28s	27 tps	164K	$0.700 / $2.50
MiniMax M1novita/bf16bf16	No data	—	100%	1.15s	1.17s	45 tps	1.0M	$0.550 / $2.20
MiniMax M2novita/fp8fp8	No data	—	99.39%	1.84s	7.66s	56 tps	205K	$0.300 / $1.20
MiniMax M2.5novita/fp8fp8	No data	—	99.88%	1.07s	4.85s	56 tps	205K	$0.300 / $1.20
MiniMax M2.7novita/fp8fp8	No data	—	99.24%	1.26s	10.4s	41 tps	205K	$0.270 / $1.08
Qwen2.5 72B Instructnovita/bf16bf16	No data	—	25.43%	2.11s	8.81s	13 tps	32K	$0.380 / $0.400
Qwen3 235B A22B Thinking 2507novita/fp8fp8	No data	—	98.94%	2.37s	6.82s	23 tps	131K	$0.300 / $3.00
Qwen3 Coder 480B A35Bnovita/fp8fp8	Degraded	—	89.01%	1.21s	16.2s	33 tps	262K	$0.380 / $1.55
Qwen3 Coder 30B A3B Instructnovita/fp8fp8	No data	—	89.83%	1.14s	8.43s	33 tps	160K	$0.070 / $0.270
Qwen3 VL 235B A22B Thinkingnovita/bf16bf16	No data	—	99.91%	977ms	6.64s	50 tps	131K	$0.980 / $3.95
Llama 3.1 Euryale 70B v2.2novita/fp8fp8	No data	—	99.93%	386ms	898ms	44 tps	8K	$1.45 / $1.45
GLM 4.5Vnovita/fp8fp8	No data	—	98.18%	1.86s	4.83s	39 tps	66K	$0.600 / $1.80
GLM 5novita/fp8fp8	No data	—	99.99%	2.74s	7.95s	66 tps	203K	$1.00 / $3.20
GLM 5.1novita/fp8fp8	No data	—	99.85%	2.04s	25.8s	43 tps	205K	$1.38 / $4.40

DeepSeek V3.1100%
Healthy24h 99.99%
p50
1.80s
p99
7.78s
Throughput
22 tps
Context
131K
$/Mtok
$0.270 / $1.00
novita/fp8fp8
R1100%
Healthy24h 100%
p50
1.02s
p99
14.9s
Throughput
21 tps
Context
64K
$/Mtok
$0.700 / $2.50
novita/fp8fp8
R1 Distill Llama 70B100%
Healthy24h 100%
p50
699ms
p99
9.12s
Throughput
28 tps
Context
8K
$/Mtok
$0.800 / $0.800
novita/bf16bf16
DeepSeek V3.1 Terminus100%
Healthy24h 100%
p50
1.87s
p99
10.9s
Throughput
21 tps
Context
131K
$/Mtok
$0.270 / $1.00
novita/fp8fp8
DeepSeek V3.2100%
Healthy24h 99.98%
p50
1.25s
p99
5.20s
Throughput
28 tps
Context
164K
$/Mtok
$0.269 / $0.400
novita/fp8fp8
DeepSeek V4 Pro 0813100%
Healthy24h 99.81%
p50
1.34s
p99
14.8s
Throughput
63 tps
Context
1.0M
$/Mtok
$1.32 / $3.96
novita/fp8fp8
Ling-2.6-1T100%
Healthy24h 100%
p50
1.37s
p99
6.75s
Throughput
68 tps
Context
262K
$/Mtok
$0.075 / $0.625
novita
Ling-2.6-flash100%
Healthy24h 99.99%
p50
562ms
p99
1.96s
Throughput
84 tps
Context
262K
$/Mtok
$0.010 / $0.030
novita
Ling-3.0-flash100%
Healthy24h 99.98%
p50
677ms
p99
5.71s
Throughput
421 tps
Context
262K
$/Mtok
$0.042 / $0.126
novita/fast
Ring-2.6-1T100%
Healthy24h 100%
p50
1.63s
p99
15.4s
Throughput
86 tps
Context
262K
$/Mtok
$0.075 / $0.625
novita
Llama 4 Maverick100%
Healthy24h 99.88%
p50
525ms
p99
1.75s
Throughput
45 tps
Context
1.0M
$/Mtok
$0.270 / $0.850
novita/fp8fp8
Llama 4 Scout100%
Healthy24h 99.15%
p50
622ms
p99
2.09s
Throughput
26 tps
Context
131K
$/Mtok
$0.180 / $0.590
novita/bf16bf16
WizardLM-2 8x22B100%
Healthy24h 100%
p50
51.2s
p99
236s
Throughput
1.0 tps
Context
66K
$/Mtok
$0.620 / $0.620
novita/bf16bf16
MiniMax M2.1100%
Healthy24h 99.82%
p50
1.82s
p99
5.68s
Throughput
33 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
Kimi K2 0711100%
Healthy24h 100%
p50
732ms
p99
22.7s
Throughput
3.0 tps
Context
131K
$/Mtok
$0.570 / $2.30
novita/fp8fp8
Kimi K2 0905100%
Healthy24h 100%
p50
637ms
p99
3.69s
Throughput
21 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/fp8fp8
Kimi K2.5100%
Healthy24h 98.28%
p50
1.15s
p99
8.20s
Throughput
35 tps
Context
262K
$/Mtok
$0.570 / $2.85
novita
Kimi K2.6100%
Healthy24h 99.56%
p50
2.01s
p99
10.0s
Throughput
40 tps
Context
262K
$/Mtok
$0.800 / $3.40
novita
Kimi K2.7 Code100%
Healthy24h 99.48%
p50
1.81s
p99
10.1s
Throughput
38 tps
Context
262K
$/Mtok
$0.912 / $3.84
novita/int4int4
Nemotron 3 Nano 30B A3B100%
Healthy24h 99.93%
p50
560ms
p99
5.31s
Throughput
157 tps
Context
262K
$/Mtok
$0.050 / $0.200
novita/fp4fp4
gpt-oss-20b100%
Healthy24h 99.92%
p50
595ms
p99
11.1s
Throughput
91 tps
Context
131K
$/Mtok
$0.040 / $0.150
novita/fp4fp4
Qwen3 Coder Next100%
Healthy24h 99.42%
p50
1.50s
p99
24.8s
Throughput
61 tps
Context
262K
$/Mtok
$0.200 / $1.50
novita/fp8fp8
Qwen3 Next 80B A3B Instruct100%
Healthy24h 99.80%
p50
593ms
p99
2.38s
Throughput
28 tps
Context
131K
$/Mtok
$0.150 / $1.50
novita/bf16bf16
Qwen3.5-122B-A10B100%
Healthy24h 99.37%
p50
991ms
p99
4.50s
Throughput
61 tps
Context
262K
$/Mtok
$0.400 / $3.20
novita/bf16bf16
Qwen3.5-27B100%
Healthy24h 99.85%
p50
1.23s
p99
6.95s
Throughput
13 tps
Context
262K
$/Mtok
$0.300 / $2.40
novita/bf16bf16
Qwen3.5 397B A17B100%
Healthy24h 97.73%
p50
684ms
p99
3.24s
Throughput
3.0 tps
Context
262K
$/Mtok
$0.600 / $3.60
novita
Llama 3 8B Lunaris100%
Healthy24h 99.98%
p50
304ms
p99
899ms
Throughput
73 tps
Context
8K
$/Mtok
$0.050 / $0.050
novita/bf16bf16
GLM 4.6V100%
Healthy24h 98.76%
p50
3.03s
p99
13.5s
Throughput
15 tps
Context
131K
$/Mtok
$0.300 / $0.900
novita/bf16bf16
DeepSeek V4 Flash 0423100%
Healthy24h 99.85%
p50
1.09s
p99
5.80s
Throughput
73 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
Ling-3.0-flash99.96%
Healthy24h 99.98%
p50
704ms
p99
1.35s
Throughput
53 tps
Context
262K
$/Mtok
$0.021 / $0.063
novita
DeepSeek V4 Pro 042399.96%
Healthy24h 99.38%
p50
1.63s
p99
7.34s
Throughput
59 tps
Context
1.0M
$/Mtok
$1.60 / $3.20
novita/fp8fp8
DeepSeek V4 Flash 073199.86%
Healthy24h 99.93%
p50
1.20s
p99
8.24s
Throughput
66 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
MiniMax M399.80%
Healthy24h 99.62%
p50
1.87s
p99
14.1s
Throughput
55 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
novita/fp8fp8
Gemma 4 26B A4B 99.76%
Healthy24h 93.35%
p50
897ms
p99
8.18s
Throughput
22 tps
Context
262K
$/Mtok
$0.130 / $0.400
novita/bf16bf16
MiMo-V2.599.67%
Healthy24h 98.05%
p50
2.94s
p99
20.5s
Throughput
34 tps
Context
1.0M
$/Mtok
$0.168 / $0.336
novita/fp8fp8
MiMo-V2.5-Pro99.64%
Healthy24h 97.45%
p50
3.68s
p99
33.9s
Throughput
26 tps
Context
1.0M
$/Mtok
$0.480 / $0.960
novita
DeepSeek V3.2 Exp99.59%
Healthy24h 99.40%
p50
1.44s
p99
7.18s
Throughput
25 tps
Context
164K
$/Mtok
$0.270 / $0.410
novita/fp8fp8
Llama 3.1 8B Instruct99.41%
Healthy24h 99.78%
p50
497ms
p99
2.53s
Throughput
59 tps
Context
16K
$/Mtok
$0.020 / $0.050
novita/fp8fp8
Qwen3 235B A22B Instruct 250799.35%
Healthy24h 99.08%
p50
696ms
p99
11.0s
Throughput
31 tps
Context
131K
$/Mtok
$0.090 / $0.580
novita/fp8fp8
GLM 4.5 Air99.31%
Healthy24h 99.27%
p50
659ms
p99
10.1s
Throughput
40 tps
Context
131K
$/Mtok
$0.130 / $0.850
novita/bf16bf16
Kimi K2 Thinking99.05%
Healthy24h 99.70%
p50
898ms
p99
7.95s
Throughput
39 tps
Context
262K
$/Mtok
$0.600 / $2.50
novita/bf16bf16
GLM 4.698.89%
Healthy24h 97.33%
p50
1.16s
p99
17.5s
Throughput
46 tps
Context
205K
$/Mtok
$0.550 / $2.20
novita/bf16bf16
GLM 5.298.36%
Healthy24h 99.57%
p50
1.62s
p99
27.0s
Throughput
34 tps
Context
1.0M
$/Mtok
$0.741 / $2.33
novita/fp8fp8
DeepSeek V3 032498.10%
Degraded24h 97.73%
p50
1.31s
p99
14.6s
Throughput
31 tps
Context
164K
$/Mtok
$0.270 / $1.12
novita/fp8fp8
Step 3.7 Flash98.04%
Healthy24h 97.70%
p50
2.79s
p99
12.2s
Throughput
9.0 tps
Context
262K
$/Mtok
$0.200 / $1.15
novita/fp8fp8
Llama 3.3 70B Instruct97.86%
Healthy24h 96.40%
p50
813ms
p99
4.58s
Throughput
27 tps
Context
12K
$/Mtok
$0.135 / $0.400
novita/bf16bf16
Gemma 4 31B97.26%
Healthy24h 82.69%
p50
1.09s
p99
9.03s
Throughput
7.0 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
Qwen3 VL 235B A22B Instruct96.59%
Healthy24h 94.76%
p50
1.32s
p99
13.2s
Throughput
14 tps
Context
131K
$/Mtok
$0.300 / $1.50
novita/bf16bf16
Qwen3 VL 30B A3B Instruct96.55%
Degraded24h 95.73%
p50
803ms
p99
6.63s
Throughput
18 tps
Context
131K
$/Mtok
$0.200 / $0.700
novita/bf16bf16
Hy393.18%
Degraded24h 99.25%
p50
1.99s
p99
8.30s
Throughput
62 tps
Context
262K
$/Mtok
$0.140 / $0.580
novita
gpt-oss-120b90.33%
Degraded24h 95.82%
p50
581ms
p99
11.3s
Throughput
61 tps
Context
131K
$/Mtok
$0.050 / $0.250
novita/fp4fp4
GLM 4.788.10%
Down24h 93.80%
p50
2.31s
p99
38.6s
Throughput
21 tps
Context
205K
$/Mtok
$0.540 / $1.98
novita/fp8fp8
DeepSeek V386.76%
Down24h 97.27%
p50
1.12s
p99
8.27s
Throughput
23 tps
Context
64K
$/Mtok
$0.400 / $1.30
novita/fp8fp8
GLM 4.7 Flash86.67%
Down24h 80.72%
p50
1.26s
p99
75.6s
Throughput
30 tps
Context
200K
$/Mtok
$0.070 / $0.400
novita/bf16bf16
Mistral Nemo71.64%
Down24h 54.06%
p50
2.45s
p99
57.1s
Throughput
9.0 tps
Context
60K
$/Mtok
$0.040 / $0.170
novita/fp8fp8
Gemma 3 27B58.98%
Down24h 87.58%
p50
901ms
p99
64.7s
Throughput
15 tps
Context
98K
$/Mtok
$0.119 / $0.200
novita/bf16bf16
ERNIE 4.5 VL 424B A47B —
No data24h 100%
p50
1.25s
p99
4.72s
Throughput
21 tps
Context
123K
$/Mtok
$0.420 / $1.25
novita/fp16fp16
R1 0528—
No data24h 100%
p50
889ms
p99
2.28s
Throughput
27 tps
Context
164K
$/Mtok
$0.700 / $2.50
novita/fp8fp8
MiniMax M1—
No data24h 100%
p50
1.15s
p99
1.17s
Throughput
45 tps
Context
1.0M
$/Mtok
$0.550 / $2.20
novita/bf16bf16
MiniMax M2—
No data24h 99.39%
p50
1.84s
p99
7.66s
Throughput
56 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.5—
No data24h 99.88%
p50
1.07s
p99
4.85s
Throughput
56 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8
MiniMax M2.7—
No data24h 99.24%
p50
1.26s
p99
10.4s
Throughput
41 tps
Context
205K
$/Mtok
$0.270 / $1.08
novita/fp8fp8
Qwen2.5 72B Instruct—
No data24h 25.43%
p50
2.11s
p99
8.81s
Throughput
13 tps
Context
32K
$/Mtok
$0.380 / $0.400
novita/bf16bf16
Qwen3 235B A22B Thinking 2507—
No data24h 98.94%
p50
2.37s
p99
6.82s
Throughput
23 tps
Context
131K
$/Mtok
$0.300 / $3.00
novita/fp8fp8
Qwen3 Coder 480B A35B—
Degraded24h 89.01%
p50
1.21s
p99
16.2s
Throughput
33 tps
Context
262K
$/Mtok
$0.380 / $1.55
novita/fp8fp8
Qwen3 Coder 30B A3B Instruct—
No data24h 89.83%
p50
1.14s
p99
8.43s
Throughput
33 tps
Context
160K
$/Mtok
$0.070 / $0.270
novita/fp8fp8
Qwen3 VL 235B A22B Thinking—
No data24h 99.91%
p50
977ms
p99
6.64s
Throughput
50 tps
Context
131K
$/Mtok
$0.980 / $3.95
novita/bf16bf16
Llama 3.1 Euryale 70B v2.2—
No data24h 99.93%
p50
386ms
p99
898ms
Throughput
44 tps
Context
8K
$/Mtok
$1.45 / $1.45
novita/fp8fp8
GLM 4.5V—
No data24h 98.18%
p50
1.86s
p99
4.83s
Throughput
39 tps
Context
66K
$/Mtok
$0.600 / $1.80
novita/fp8fp8
GLM 5—
No data24h 99.99%
p50
2.74s
p99
7.95s
Throughput
66 tps
Context
203K
$/Mtok
$1.00 / $3.20
novita/fp8fp8
GLM 5.1—
No data24h 99.85%
p50
2.04s
p99
25.8s
Throughput
43 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.