SiliconFlow

37 endpoints · 4 unhealthy · worst uptime 88.01%

	State
DeepSeek V3.2siliconflow/fp8fp8	Healthy	100%	99.72%	2.07s	7.26s	26 tps	164K	$0.259 / $0.420
DeepSeek V3.2 Expsiliconflow/fp8fp8	Healthy	100%	99.94%	1.73s	6.95s	24 tps	164K	$0.270 / $0.410
DeepSeek V4 Pro 0423siliconflow/fp8fp8	Healthy	100%	98.15%	1.84s	9.11s	42 tps	1.0M	$1.50 / $3.14
DeepSeek V4 Pro 0813siliconflow/fp8fp8	Healthy	100%	99.59%	1.51s	16.4s	44 tps	1.0M	$1.32 / $3.96
Kimi K2.5siliconflow/int4int4	Healthy	100%	99.97%	1.58s	49.0s	43 tps	262K	$0.450 / $2.25
Kimi K2.6siliconflow/fp8fp8	Healthy	100%	99.77%	923ms	6.26s	33 tps	262K	$0.770 / $3.40
Qwen3.5-122B-A10Bsiliconflow/fp8fp8	Healthy	100%	97.34%	1.88s	5.11s	34 tps	262K	$0.260 / $2.08
Qwen3.5-27Bsiliconflow/fp8fp8	Healthy	100%	98.53%	1.43s	7.18s	12 tps	262K	$0.250 / $2.00
Qwen3.6 35B A3Bsiliconflow/fp8fp8	Healthy	100%	98.85%	1.48s	18.7s	59 tps	262K	$0.200 / $1.60
Qwen3.8 2.4T A95Bsiliconflow/fp8fp8	Healthy	100%	99.50%	2.78s	22.2s	36 tps	1.0M	$2.00 / $6.00
Step 3.5 Flashsiliconflow/fp8fp8	Healthy	100%	100%	1.22s	3.57s	55 tps	262K	$0.100 / $0.300
GLM 4.5 Airsiliconflow/fp8fp8	Healthy	100%	99.29%	1.45s	6.61s	22 tps	131K	$0.140 / $0.860
GLM 5.1siliconflow/fp8fp8	Healthy	100%	99.87%	2.54s	15.0s	37 tps	205K	$1.19 / $3.74
GLM 5.2siliconflow/fp8fp8	Healthy	100%	99.29%	1.90s	38.4s	56 tps	1.0M	$1.19 / $3.74
DeepSeek V4 Flash 0423siliconflow/fp8fp8	Healthy	99.93%	99.37%	1.37s	9.82s	46 tps	1.0M	$0.130 / $0.280
Qwen3 32Bsiliconflow/fp8fp8	Healthy	99.76%	93.38%	1.57s	7.77s	19 tps	131K	$0.140 / $0.570
DeepSeek V3.1siliconflow/fp8fp8	Healthy	99.55%	98.02%	1.51s	11.4s	15 tps	164K	$0.270 / $1.00
gpt-oss-120bsiliconflow/fp8fp8	Healthy	99.31%	93.85%	1.41s	25.3s	20 tps	131K	$0.050 / $0.450
Qwen3 VL 30B A3B Instructsiliconflow/fp8fp8	Healthy	98.90%	97.61%	2.41s	6.75s	11 tps	262K	$0.290 / $1.00
DeepSeek V4 Flash 0731siliconflow/fp8fp8	Healthy	98.86%	98.84%	1.35s	15.4s	60 tps	1.0M	$0.140 / $0.280
R1 0528siliconflow/fp8fp8	Healthy	98.46%	99.53%	2.02s	14.9s	17 tps	164K	$0.500 / $2.18
Gemma 4 26B A4B siliconflow/fp8fp8	Healthy	98.29%	99.03%	1.48s	6.18s	24 tps	262K	$0.120 / $0.400
DeepSeek V3 0324siliconflow/fp8fp8	Healthy	97.58%	96.57%	1.40s	10.7s	19 tps	164K	$0.250 / $1.00
GLM 5siliconflow/fp8fp8	Healthy	97.56%	99.87%	2.30s	13.6s	42 tps	205K	$0.950 / $2.55
Qwen3 Coder 30B A3B Instructsiliconflow/fp8fp8	Healthy	97.22%	95.67%	2.53s	26.2s	18 tps	262K	$0.070 / $0.280
Qwen3.6 27Bsiliconflow/fp8fp8	Healthy	97.22%	92.71%	1.50s	14.4s	21 tps	262K	$0.300 / $3.20
Qwen3.5-9Bsiliconflow/fp8fp8	Healthy	96.50%	98.43%	1.77s	5.91s	9.0 tps	262K	$0.100 / $0.150
DeepSeek V3.1 Terminussiliconflow/fp8fp8	Healthy	96.22%	98.23%	1.43s	10.5s	16 tps	164K	$0.270 / $1.00
Qwen3 30B A3B Instruct 2507siliconflow/fp8fp8	Degraded	94.99%	89.14%	2.06s	8.44s	16 tps	262K	$0.090 / $0.300
Qwen3.5-35B-A3Bsiliconflow/fp8fp8	Degraded	94.38%	98.05%	1.30s	11.6s	44 tps	262K	$0.240 / $1.80
Gemma 4 31Bsiliconflow/fp8fp8	Degraded	91.17%	84.81%	2.57s	17.4s	23 tps	262K	$0.130 / $0.400
gpt-oss-20bsiliconflow/fp8fp8	Down	88.01%	98.14%	1.23s	20.3s	29 tps	131K	$0.040 / $0.180
MiniMax M2.5siliconflow/fp8fp8	No data	—	99.97%	1.18s	3.01s	45 tps	197K	$0.300 / $1.20
Kimi K2.7 Codesiliconflow/fp8fp8	No data	—	99.95%	2.47s	9.83s	7.0 tps	262K	$0.859 / $3.80
Nex-N2-Prosiliconflow	No data	—	99.24%	850ms	1.48s	11 tps	262K	$0.500 / $2.50
Qwen3 VL 30B A3B Thinkingsiliconflow/fp8fp8	No data	—	99.82%	1.23s	3.82s	53 tps	262K	$0.290 / $1.00
Hunyuan A13B Instructsiliconflow/fp8fp8	No data	—	100%	1.15s	5.13s	26 tps	131K	$0.140 / $0.570

DeepSeek V3.2100%
Healthy24h 99.72%
p50
2.07s
p99
7.26s
Throughput
26 tps
Context
164K
$/Mtok
$0.259 / $0.420
siliconflow/fp8fp8
DeepSeek V3.2 Exp100%
Healthy24h 99.94%
p50
1.73s
p99
6.95s
Throughput
24 tps
Context
164K
$/Mtok
$0.270 / $0.410
siliconflow/fp8fp8
DeepSeek V4 Pro 0423100%
Healthy24h 98.15%
p50
1.84s
p99
9.11s
Throughput
42 tps
Context
1.0M
$/Mtok
$1.50 / $3.14
siliconflow/fp8fp8
DeepSeek V4 Pro 0813100%
Healthy24h 99.59%
p50
1.51s
p99
16.4s
Throughput
44 tps
Context
1.0M
$/Mtok
$1.32 / $3.96
siliconflow/fp8fp8
Kimi K2.5100%
Healthy24h 99.97%
p50
1.58s
p99
49.0s
Throughput
43 tps
Context
262K
$/Mtok
$0.450 / $2.25
siliconflow/int4int4
Kimi K2.6100%
Healthy24h 99.77%
p50
923ms
p99
6.26s
Throughput
33 tps
Context
262K
$/Mtok
$0.770 / $3.40
siliconflow/fp8fp8
Qwen3.5-122B-A10B100%
Healthy24h 97.34%
p50
1.88s
p99
5.11s
Throughput
34 tps
Context
262K
$/Mtok
$0.260 / $2.08
siliconflow/fp8fp8
Qwen3.5-27B100%
Healthy24h 98.53%
p50
1.43s
p99
7.18s
Throughput
12 tps
Context
262K
$/Mtok
$0.250 / $2.00
siliconflow/fp8fp8
Qwen3.6 35B A3B100%
Healthy24h 98.85%
p50
1.48s
p99
18.7s
Throughput
59 tps
Context
262K
$/Mtok
$0.200 / $1.60
siliconflow/fp8fp8
Qwen3.8 2.4T A95B100%
Healthy24h 99.50%
p50
2.78s
p99
22.2s
Throughput
36 tps
Context
1.0M
$/Mtok
$2.00 / $6.00
siliconflow/fp8fp8
Step 3.5 Flash100%
Healthy24h 100%
p50
1.22s
p99
3.57s
Throughput
55 tps
Context
262K
$/Mtok
$0.100 / $0.300
siliconflow/fp8fp8
GLM 4.5 Air100%
Healthy24h 99.29%
p50
1.45s
p99
6.61s
Throughput
22 tps
Context
131K
$/Mtok
$0.140 / $0.860
siliconflow/fp8fp8
GLM 5.1100%
Healthy24h 99.87%
p50
2.54s
p99
15.0s
Throughput
37 tps
Context
205K
$/Mtok
$1.19 / $3.74
siliconflow/fp8fp8
GLM 5.2100%
Healthy24h 99.29%
p50
1.90s
p99
38.4s
Throughput
56 tps
Context
1.0M
$/Mtok
$1.19 / $3.74
siliconflow/fp8fp8
DeepSeek V4 Flash 042399.93%
Healthy24h 99.37%
p50
1.37s
p99
9.82s
Throughput
46 tps
Context
1.0M
$/Mtok
$0.130 / $0.280
siliconflow/fp8fp8
Qwen3 32B99.76%
Healthy24h 93.38%
p50
1.57s
p99
7.77s
Throughput
19 tps
Context
131K
$/Mtok
$0.140 / $0.570
siliconflow/fp8fp8
DeepSeek V3.199.55%
Healthy24h 98.02%
p50
1.51s
p99
11.4s
Throughput
15 tps
Context
164K
$/Mtok
$0.270 / $1.00
siliconflow/fp8fp8
gpt-oss-120b99.31%
Healthy24h 93.85%
p50
1.41s
p99
25.3s
Throughput
20 tps
Context
131K
$/Mtok
$0.050 / $0.450
siliconflow/fp8fp8
Qwen3 VL 30B A3B Instruct98.90%
Healthy24h 97.61%
p50
2.41s
p99
6.75s
Throughput
11 tps
Context
262K
$/Mtok
$0.290 / $1.00
siliconflow/fp8fp8
DeepSeek V4 Flash 073198.86%
Healthy24h 98.84%
p50
1.35s
p99
15.4s
Throughput
60 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
siliconflow/fp8fp8
R1 052898.46%
Healthy24h 99.53%
p50
2.02s
p99
14.9s
Throughput
17 tps
Context
164K
$/Mtok
$0.500 / $2.18
siliconflow/fp8fp8
Gemma 4 26B A4B 98.29%
Healthy24h 99.03%
p50
1.48s
p99
6.18s
Throughput
24 tps
Context
262K
$/Mtok
$0.120 / $0.400
siliconflow/fp8fp8
DeepSeek V3 032497.58%
Healthy24h 96.57%
p50
1.40s
p99
10.7s
Throughput
19 tps
Context
164K
$/Mtok
$0.250 / $1.00
siliconflow/fp8fp8
GLM 597.56%
Healthy24h 99.87%
p50
2.30s
p99
13.6s
Throughput
42 tps
Context
205K
$/Mtok
$0.950 / $2.55
siliconflow/fp8fp8
Qwen3 Coder 30B A3B Instruct97.22%
Healthy24h 95.67%
p50
2.53s
p99
26.2s
Throughput
18 tps
Context
262K
$/Mtok
$0.070 / $0.280
siliconflow/fp8fp8
Qwen3.6 27B97.22%
Healthy24h 92.71%
p50
1.50s
p99
14.4s
Throughput
21 tps
Context
262K
$/Mtok
$0.300 / $3.20
siliconflow/fp8fp8
Qwen3.5-9B96.50%
Healthy24h 98.43%
p50
1.77s
p99
5.91s
Throughput
9.0 tps
Context
262K
$/Mtok
$0.100 / $0.150
siliconflow/fp8fp8
DeepSeek V3.1 Terminus96.22%
Healthy24h 98.23%
p50
1.43s
p99
10.5s
Throughput
16 tps
Context
164K
$/Mtok
$0.270 / $1.00
siliconflow/fp8fp8
Qwen3 30B A3B Instruct 250794.99%
Degraded24h 89.14%
p50
2.06s
p99
8.44s
Throughput
16 tps
Context
262K
$/Mtok
$0.090 / $0.300
siliconflow/fp8fp8
Qwen3.5-35B-A3B94.38%
Degraded24h 98.05%
p50
1.30s
p99
11.6s
Throughput
44 tps
Context
262K
$/Mtok
$0.240 / $1.80
siliconflow/fp8fp8
Gemma 4 31B91.17%
Degraded24h 84.81%
p50
2.57s
p99
17.4s
Throughput
23 tps
Context
262K
$/Mtok
$0.130 / $0.400
siliconflow/fp8fp8
gpt-oss-20b88.01%
Down24h 98.14%
p50
1.23s
p99
20.3s
Throughput
29 tps
Context
131K
$/Mtok
$0.040 / $0.180
siliconflow/fp8fp8
MiniMax M2.5—
No data24h 99.97%
p50
1.18s
p99
3.01s
Throughput
45 tps
Context
197K
$/Mtok
$0.300 / $1.20
siliconflow/fp8fp8
Kimi K2.7 Code—
No data24h 99.95%
p50
2.47s
p99
9.83s
Throughput
7.0 tps
Context
262K
$/Mtok
$0.859 / $3.80
siliconflow/fp8fp8
Nex-N2-Pro—
No data24h 99.24%
p50
850ms
p99
1.48s
Throughput
11 tps
Context
262K
$/Mtok
$0.500 / $2.50
siliconflow
Qwen3 VL 30B A3B Thinking—
No data24h 99.82%
p50
1.23s
p99
3.82s
Throughput
53 tps
Context
262K
$/Mtok
$0.290 / $1.00
siliconflow/fp8fp8
Hunyuan A13B Instruct—
No data24h 100%
p50
1.15s
p99
5.13s
Throughput
26 tps
Context
131K
$/Mtok
$0.140 / $0.570
siliconflow/fp8fp8

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.