DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flashInputOutput

Compare its 25 providers Incident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash Vision Exp, DeepSeek V4.1 Flash

CompareDeepSeek V4 Flash 0423

	State
Azureazure/us	Healthy	100%	97.55%	97.59%	95.92%	2.13s	24.1s	50 tps	1.0M	$0.210 / $0.560
Cloudflarecloudflare	Healthy	100%	99.91%	99.93%	99.93%	1.91s	18.6s	59 tps	384K	$0.440 / $1.32
Mancer 2mancer/fp8fp8	Healthy	100%	99.09%	97.57%	98.05%	725ms	11.9s	34 tps	1.0M	$0.190 / $0.500
Novitanovita/fp8fp8	Healthy	100%	99.96%	99.95%	99.93%	1.37s	4.98s	67 tps	1.0M	$0.140 / $0.280
GMICloudgmicloud/fp8fp8	Healthy	100%	99.85%	99.97%	99.69%	1.50s	4.42s	56 tps	1.0M	$0.091 / $0.182
Baidubaidu/fp8fp8	Healthy	99.99%	98.65%	89.43%	96.38%	974ms	6.15s	72 tps	1.0M	$0.140 / $0.280
Relacerelace/fp4fp4	Healthy	99.96%	99.93%	99.64%	99.71%	582ms	7.93s	92 tps	1.0M	$0.022 / $1.28
DigitalOceandigitalocean	Healthy	99.92%	99.71%	99.82%	99.83%	747ms	6.46s	24 tps	1.0M	$0.098 / $0.196
AtlasCloudatlas-cloud/fp4fp4	Healthy	99.92%	99.10%	98.41%	99.29%	2.06s	23.8s	53 tps	1.0M	$0.140 / $0.280
Parasailparasail/fp8fp8	Healthy	99.91%	99.80%	99.83%	99.72%	673ms	3.42s	55 tps	1.0M	$0.140 / $0.280
Venicevenice	Healthy	99.91%	99.42%	98.94%	98.44%	1.02s	9.03s	44 tps	1.0M	$0.097 / $0.193
DeepInfradeepinfra/fp8fp8	Healthy	99.88%	99.92%	99.51%	99.50%	909ms	6.19s	49 tps	1.0M	$0.090 / $0.180
SiliconFlowsiliconflow/fp8fp8	Healthy	99.81%	99.85%	99.70%	98.29%	1.10s	7.41s	44 tps	1.0M	$0.130 / $0.280
OpenInferenceopen-inference/fp4fp4	Healthy	99.76%	99.52%	98.24%	98.24%	1.09s	9.26s	33 tps	1.0M	$0.029 / $1.66
Alibabaalibaba/fp8fp8	Healthy	99.09%	97.69%	98.73%	99.12%	838ms	7.41s	96 tps	1.0M	$0.134 / $0.268
StreamLakestreamlake/fp8fp8	Healthy	98.56%	99.71%	99.04%	97.70%	1.71s	9.66s	51 tps	1.0M	$0.028 / $0.056
CoreWeavecoreweave/fp8fp8	No data	—	—	—	—	—	—	—	1.0M	$0.140 / $0.280
Crusoecrusoe/fp8fp8	No data	—	—	—	—	—	—	—	1.0M	$0.140 / $0.280
DeepSeekdeepseek	No data	—	—	—	—	—	—	—	1.0M	$0.220 / $0.660
NextBitnextbit/fp8fp8	No data	—	—	—	99.37%	—	—	—	1.0M	$0.150 / $0.300
OpenInferenceopen-inference/fp8fp8	No data	—	—	95.39%	97.88%	—	—	—	1.0M	$0.002 / $1.31
Phalaphala	No data	—	—	—	98.93%	—	—	—	1.0M	$0.200 / $0.400
Rekareka	No data	—	—	98.07%	98.07%	—	—	—	1.0M	$0.130 / $0.260
Sail Researchsail-research/fp4fp4	No data	—	—	—	—	—	—	—	1.0M	$0.090 / $0.180
Waferwafer	No data	—	—	—	99.43%	—	—	—	1.0M	$0.100 / $0.250

Azure100%
Healthy24h 97.55%
7d
97.59%
30d
95.92%
p50
2.13s
p99
24.1s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.210 / $0.560
azure/us
Cloudflare100%
Healthy24h 99.91%
7d
99.93%
30d
99.93%
p50
1.91s
p99
18.6s
Throughput
59 tps
Context
384K
$/Mtok
$0.440 / $1.32
cloudflare
Mancer 2100%
Healthy24h 99.09%
7d
97.57%
30d
98.05%
p50
725ms
p99
11.9s
Throughput
34 tps
Context
1.0M
$/Mtok
$0.190 / $0.500
mancer/fp8fp8
Novita100%
Healthy24h 99.96%
7d
99.95%
30d
99.93%
p50
1.37s
p99
4.98s
Throughput
67 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
novita/fp8fp8
GMICloud100%
Healthy24h 99.85%
7d
99.97%
30d
99.69%
p50
1.50s
p99
4.42s
Throughput
56 tps
Context
1.0M
$/Mtok
$0.091 / $0.182
gmicloud/fp8fp8
Baidu99.99%
Healthy24h 98.65%
7d
89.43%
30d
96.38%
p50
974ms
p99
6.15s
Throughput
72 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
baidu/fp8fp8
Relace99.96%
Healthy24h 99.93%
7d
99.64%
30d
99.71%
p50
582ms
p99
7.93s
Throughput
92 tps
Context
1.0M
$/Mtok
$0.022 / $1.28
relace/fp4fp4
DigitalOcean99.92%
Healthy24h 99.71%
7d
99.82%
30d
99.83%
p50
747ms
p99
6.46s
Throughput
24 tps
Context
1.0M
$/Mtok
$0.098 / $0.196
digitalocean
AtlasCloud99.92%
Healthy24h 99.10%
7d
98.41%
30d
99.29%
p50
2.06s
p99
23.8s
Throughput
53 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
atlas-cloud/fp4fp4
Parasail99.91%
Healthy24h 99.80%
7d
99.83%
30d
99.72%
p50
673ms
p99
3.42s
Throughput
55 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
parasail/fp8fp8
Venice99.91%
Healthy24h 99.42%
7d
98.94%
30d
98.44%
p50
1.02s
p99
9.03s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.097 / $0.193
venice
DeepInfra99.88%
Healthy24h 99.92%
7d
99.51%
30d
99.50%
p50
909ms
p99
6.19s
Throughput
49 tps
Context
1.0M
$/Mtok
$0.090 / $0.180
deepinfra/fp8fp8
SiliconFlow99.81%
Healthy24h 99.85%
7d
99.70%
30d
98.29%
p50
1.10s
p99
7.41s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.130 / $0.280
siliconflow/fp8fp8
OpenInference99.76%
Healthy24h 99.52%
7d
98.24%
30d
98.24%
p50
1.09s
p99
9.26s
Throughput
33 tps
Context
1.0M
$/Mtok
$0.029 / $1.66
open-inference/fp4fp4
Alibaba99.09%
Healthy24h 97.69%
7d
98.73%
30d
99.12%
p50
838ms
p99
7.41s
Throughput
96 tps
Context
1.0M
$/Mtok
$0.134 / $0.268
alibaba/fp8fp8
StreamLake98.56%
Healthy24h 99.71%
7d
99.04%
30d
97.70%
p50
1.71s
p99
9.66s
Throughput
51 tps
Context
1.0M
$/Mtok
$0.028 / $0.056
streamlake/fp8fp8
CoreWeave—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.140 / $0.280
coreweave/fp8fp8
Crusoe—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.140 / $0.280
crusoe/fp8fp8
DeepSeek—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.220 / $0.660
deepseek
NextBit—
No data24h —
7d
—
30d
99.37%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.150 / $0.300
nextbit/fp8fp8
OpenInference—
No data24h —
7d
95.39%
30d
97.88%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.002 / $1.31
open-inference/fp8fp8
Phala—
No data24h —
7d
—
30d
98.93%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.200 / $0.400
phala
Reka—
No data24h —
7d
98.07%
30d
98.07%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.130 / $0.260
reka
Sail Research—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.090 / $0.180
sail-research/fp4fp4
Wafer—
No data24h —
7d
—
30d
99.43%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.100 / $0.250
wafer

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

7 endpoints have no chartable data in this range.

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 24 endpoints · 48 days with data, 129 endpoint-days below 90%.

Price changes

DeepSeek V4 Flash 0423 Relacerelace/fp4$0.022 / $1.28cache read $0.020 → $0.0222026-10-04 05:35 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.029 / $1.66cache read $0.026 → $0.0292026-10-04 05:35 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.022 / $1.28cache read $0.022 → $0.0202026-10-04 05:31 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.029 / $1.66cache read $0.029 → $0.0262026-10-04 05:31 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.029 / $1.66cache read $0.026 → $0.0292026-10-04 05:25 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.022 / $1.28cache read $0.020 → $0.0222026-10-04 05:20 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.036 → $0.029 / $1.66cache read $0.032 → $0.0262026-10-03 22:05 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.028 → $0.022 / $1.28cache read $0.025 → $0.0202026-10-03 22:01 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.036 / $1.66cache read $0.036 → $0.0322026-10-03 21:45 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.028 / $1.28cache read $0.028 → $0.0252026-10-03 21:40 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.033 → $0.036 / $1.66cache read $0.033 → $0.0362026-10-03 10:01 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.025 → $0.028 / $1.28cache read $0.025 → $0.0282026-10-03 09:55 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.028 → $0.033 / $1.66cache read $0.028 → $0.0332026-10-03 09:01 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.022 → $0.025 / $1.28cache read $0.022 → $0.0252026-10-03 08:50 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.024 → $0.028 / $1.66cache read $0.024 → $0.0282026-10-03 08:31 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.018 → $0.022 / $1.28cache read $0.018 → $0.0222026-10-03 08:25 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.020 → $0.024 / $1.66cache read $0.018 → $0.0242026-10-03 08:15 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.016 → $0.018 / $1.28cache read $0.014 → $0.0182026-10-03 08:10 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.017 → $0.020 / $1.66cache read $0.016 → $0.0182026-10-03 07:55 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.013 → $0.016 / $1.28cache read $0.012 → $0.0142026-10-03 07:45 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.015 → $0.017 / $1.66cache read $0.014 → $0.0162026-10-03 07:35 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.011 → $0.013 / $1.28cache read $0.010 → $0.0122026-10-03 07:10 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.013 → $0.015 / $1.66cache read $0.012 → $0.0142026-10-03 06:55 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.010 → $0.011 / $1.28cache read $0.009 → $0.0102026-10-03 06:45 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.011 → $0.013 / $1.66cache read $0.010 → $0.0122026-10-03 06:30 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.009 → $0.010 / $1.28cache read $0.008 → $0.0092026-10-03 06:25 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.009 → $0.011 / $1.66cache read $0.008 → $0.0102026-10-03 06:10 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.007 → $0.009 / $1.28cache read $0.006 → $0.0082026-10-03 06:01 UTC
DeepSeek V4 Flash 0423 OpenInferenceopen-inference/fp4$0.009 → $0.009 / $1.66cache read $0.009 → $0.0082026-10-03 06:01 UTC
DeepSeek V4 Flash 0423 Relacerelace/fp4$0.007 → $0.007 / $1.28cache read $0.007 → $0.0062026-10-03 05:50 UTC