DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flashInputOutput

Compare its 25 providers Incident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp

CompareDeepSeek V4.1 Flash

	State
Alibabaalibaba	Healthy	100%	99.56%	99.77%	99.77%	1.75s	17.6s	79 tps	1.0M	$0.300 / $1.20
AtlasCloudatlas-cloud/fp8fp8	Healthy	100%	99.83%	99.81%	99.81%	1.39s	9.95s	72 tps	1.0M	$0.300 / $1.20
BaseTenbaseten/fp8fp8	Healthy	100%	98.82%	99.81%	99.81%	434ms	5.85s	83 tps	1.0M	$0.300 / $1.20
Fireworksfireworks	Healthy	100%	99.82%	99.27%	99.24%	1.14s	12.7s	63 tps	1.0M	$0.220 / $0.660
Modalmodal	Healthy	100%	98.70%	97.83%	97.72%	727ms	12.5s	125 tps	1.0M	$0.300 / $1.20
Relacerelace/fp4fp4	Healthy	100%	99.34%	98.61%	98.61%	1.08s	7.17s	61 tps	1.0M	$0.150 / $0.600
StreamLakestreamlake/fp8fp8	Healthy	100%	99.32%	99.47%	99.47%	2.50s	14.2s	65 tps	1.0M	$0.282 / $1.13
Venicevenice/fp8fp8	Healthy	100%	97.70%	98.83%	98.83%	1.03s	12.8s	87 tps	1.0M	$0.375 / $1.50
Waferwafer	Healthy	100%	98.89%	99.11%	99.11%	633ms	10.8s	102 tps	1.0M	$0.200 / $0.600
Togethertogether	Healthy	99.98%	99.92%	98.30%	98.30%	328ms	44.9s	126 tps	1.0M	$0.300 / $1.20
DeepSeekdeepseek	Healthy	99.95%	99.98%	98.27%	98.45%	751ms	13.5s	128 tps	1.0M	$0.150 / $0.600
Morphmorph/fp8fp8	Healthy	99.93%	99.77%	95.09%	94.43%	2.32s	16.3s	13 tps	1.0M	$0.135 / $0.540
Novitanovita/fp8fp8	Healthy	99.89%	99.95%	98.74%	98.86%	2.24s	26.2s	96 tps	1.0M	$0.285 / $1.14
DeepInfradeepinfra/fp8fp8	Healthy	99.89%	99.80%	96.54%	96.16%	1.43s	12.2s	51 tps	1.0M	$0.140 / $0.420
GMICloudgmicloud/fp8fp8	Healthy	99.83%	99.80%	98.12%	98.30%	2.31s	8.45s	97 tps	1.0M	$0.285 / $1.14
SiliconFlowsiliconflow/fp8fp8	Healthy	99.75%	99.47%	96.29%	96.61%	1.55s	9.22s	91 tps	1.0M	$0.300 / $1.20
Phalaphala	Healthy	99.68%	99.76%	97.47%	97.47%	2.00s	14.8s	125 tps	1.0M	$0.345 / $1.38
DigitalOceandigitalocean	Healthy	99.37%	98.80%	96.90%	96.90%	774ms	12.4s	42 tps	1.0M	$0.300 / $1.20
Parasailparasail/fp8fp8	Healthy	98.68%	95.88%	96.66%	96.66%	916ms	22.4s	137 tps	1.0M	$0.300 / $1.20
Makoramakora	Healthy	98.02%	98.52%	97.51%	97.51%	1.19s	40.6s	144 tps	1.0M	$0.300 / $1.20
Io Netio-net/fp8fp8	No data	—	—	96.67%	96.52%	—	—	—	262K	$0.285 / $1.14
Kreakrea/fp8fp8	No data	—	—	90.32%	90.32%	—	—	—	1.0M	$0.225 / $0.900
Nebiusnebius/fp8fp8	No data	—	—	—	—	—	—	—	1.0M	$0.300 / $1.20
Rekareka/fp4fp4	No data	—	—	87.31%	87.31%	—	—	—	262K	$0.290 / $1.16
StreamLakestreamlake	No data	—	—	98.65%	98.65%	—	—	—	1.0M	$0.300 / $1.20

Alibaba100%
Healthy24h 99.56%
7d
99.77%
30d
99.77%
p50
1.75s
p99
17.6s
Throughput
79 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
alibaba
AtlasCloud100%
Healthy24h 99.83%
7d
99.81%
30d
99.81%
p50
1.39s
p99
9.95s
Throughput
72 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
atlas-cloud/fp8fp8
BaseTen100%
Healthy24h 98.82%
7d
99.81%
30d
99.81%
p50
434ms
p99
5.85s
Throughput
83 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
baseten/fp8fp8
Fireworks100%
Healthy24h 99.82%
7d
99.27%
30d
99.24%
p50
1.14s
p99
12.7s
Throughput
63 tps
Context
1.0M
$/Mtok
$0.220 / $0.660
fireworks
Modal100%
Healthy24h 98.70%
7d
97.83%
30d
97.72%
p50
727ms
p99
12.5s
Throughput
125 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
modal
Relace100%
Healthy24h 99.34%
7d
98.61%
30d
98.61%
p50
1.08s
p99
7.17s
Throughput
61 tps
Context
1.0M
$/Mtok
$0.150 / $0.600
relace/fp4fp4
StreamLake100%
Healthy24h 99.32%
7d
99.47%
30d
99.47%
p50
2.50s
p99
14.2s
Throughput
65 tps
Context
1.0M
$/Mtok
$0.282 / $1.13
streamlake/fp8fp8
Venice100%
Healthy24h 97.70%
7d
98.83%
30d
98.83%
p50
1.03s
p99
12.8s
Throughput
87 tps
Context
1.0M
$/Mtok
$0.375 / $1.50
venice/fp8fp8
Wafer100%
Healthy24h 98.89%
7d
99.11%
30d
99.11%
p50
633ms
p99
10.8s
Throughput
102 tps
Context
1.0M
$/Mtok
$0.200 / $0.600
wafer
Together99.98%
Healthy24h 99.92%
7d
98.30%
30d
98.30%
p50
328ms
p99
44.9s
Throughput
126 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
together
DeepSeek99.95%
Healthy24h 99.98%
7d
98.27%
30d
98.45%
p50
751ms
p99
13.5s
Throughput
128 tps
Context
1.0M
$/Mtok
$0.150 / $0.600
deepseek
Morph99.93%
Healthy24h 99.77%
7d
95.09%
30d
94.43%
p50
2.32s
p99
16.3s
Throughput
13 tps
Context
1.0M
$/Mtok
$0.135 / $0.540
morph/fp8fp8
Novita99.89%
Healthy24h 99.95%
7d
98.74%
30d
98.86%
p50
2.24s
p99
26.2s
Throughput
96 tps
Context
1.0M
$/Mtok
$0.285 / $1.14
novita/fp8fp8
DeepInfra99.89%
Healthy24h 99.80%
7d
96.54%
30d
96.16%
p50
1.43s
p99
12.2s
Throughput
51 tps
Context
1.0M
$/Mtok
$0.140 / $0.420
deepinfra/fp8fp8
GMICloud99.83%
Healthy24h 99.80%
7d
98.12%
30d
98.30%
p50
2.31s
p99
8.45s
Throughput
97 tps
Context
1.0M
$/Mtok
$0.285 / $1.14
gmicloud/fp8fp8
SiliconFlow99.75%
Healthy24h 99.47%
7d
96.29%
30d
96.61%
p50
1.55s
p99
9.22s
Throughput
91 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
siliconflow/fp8fp8
Phala99.68%
Healthy24h 99.76%
7d
97.47%
30d
97.47%
p50
2.00s
p99
14.8s
Throughput
125 tps
Context
1.0M
$/Mtok
$0.345 / $1.38
phala
DigitalOcean99.37%
Healthy24h 98.80%
7d
96.90%
30d
96.90%
p50
774ms
p99
12.4s
Throughput
42 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
digitalocean
Parasail98.68%
Healthy24h 95.88%
7d
96.66%
30d
96.66%
p50
916ms
p99
22.4s
Throughput
137 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
parasail/fp8fp8
Makora98.02%
Healthy24h 98.52%
7d
97.51%
30d
97.51%
p50
1.19s
p99
40.6s
Throughput
144 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
makora
Io Net—
No data24h —
7d
96.67%
30d
96.52%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.285 / $1.14
io-net/fp8fp8
Krea—
No data24h —
7d
90.32%
30d
90.32%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.225 / $0.900
krea/fp8fp8
Nebius—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.300 / $1.20
nebius/fp8fp8
Reka—
No data24h —
7d
87.31%
30d
87.31%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.290 / $1.16
reka/fp4fp4
StreamLake—
No data24h —
7d
98.65%
30d
98.65%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.300 / $1.20
streamlake

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

1 endpoint has 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 · 9 days with data, 26 endpoint-days below 90%.

Price changes

DeepSeek V4.1 Flash Alibabaalibaba$0.150 → $0.300 / $0.600 → $1.20cache read $0.015 → $0.0302026-09-19 00:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.213 → $0.135 / $0.853 → $0.540cache read $0.006 → $0.0042026-09-18 22:15 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.194 → $0.213 / $0.776 → $0.853cache read $0.006 → $0.0062026-09-18 20:10 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.194 → $0.194 / $0.774 → $0.776cache read $0.006 → $0.0062026-09-18 20:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.150 → $0.194 / $0.600 → $0.774cache read $0.004 → $0.0062026-09-18 19:55 UTC
DeepSeek V4.1 Flash DeepInfradeepinfra/fp8$0.200 → $0.140 / $0.600 → $0.420cache read $0.006 → $0.0042026-09-18 18:20 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.213 → $0.150 / $0.853 → $0.600cache read $0.006 → $0.0042026-09-18 18:15 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.212 → $0.213 / $0.848 → $0.853cache read $0.006 → $0.0062026-09-18 15:15 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.195 → $0.212 / $0.780 → $0.848cache read $0.006 → $0.0062026-09-18 15:05 UTC
DeepSeek V4.1 Flash Alibabaalibaba$0.300 → $0.150 / $1.20 → $0.600cache read $0.030 → $0.0152026-09-18 14:10 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.149 → $0.195 / $0.594 → $0.780cache read $0.004 → $0.0062026-09-18 10:35 UTC
DeepSeek V4.1 Flash DeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-18 10:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.135 → $0.149 / $0.540 → $0.594cache read $0.004 → $0.0042026-09-18 09:05 UTC
DeepSeek V4.1 Flash Novitanovita/fp8$0.300 → $0.285 / $1.20 → $1.14cache read $0.006 → $0.0062026-09-18 07:25 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.180 → $0.135 / $0.720 → $0.540cache read $0.005 → $0.0042026-09-18 07:15 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.240 → $0.180 / $0.960 → $0.720cache read $0.007 → $0.0052026-09-18 06:20 UTC
DeepSeek V4.1 Flash DeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-09-18 06:06 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.225 → $0.240 / $0.900 → $0.960cache read $0.007 → $0.0072026-09-18 05:00 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.210 → $0.225 / $0.840 → $0.900cache read $0.006 → $0.0072026-09-18 04:40 UTC
DeepSeek V4.1 Flash DeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-18 04:05 UTC
DeepSeek V4.1 Flash Waferwafer$0.300 → $0.200 / $1.20 → $0.6002026-09-18 04:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.225 → $0.210 / $0.900 → $0.840cache read $0.007 → $0.0062026-09-18 01:10 UTC
DeepSeek V4.1 Flash DeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-09-18 01:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.210 → $0.225 / $0.840 → $0.900cache read $0.006 → $0.0072026-09-18 00:10 UTC
DeepSeek V4.1 Flash Alibabaalibaba$0.150 → $0.300 / $0.600 → $1.20cache read $0.015 → $0.0302026-09-18 00:05 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.135 → $0.210 / $0.540 → $0.840cache read $0.004 → $0.0062026-09-17 23:40 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.210 → $0.135 / $0.840 → $0.540cache read $0.006 → $0.0042026-09-17 22:25 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.150 → $0.210 / $0.600 → $0.840cache read $0.004 → $0.0062026-09-17 20:30 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.180 → $0.150 / $0.720 → $0.600cache read $0.005 → $0.0042026-09-17 19:20 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.195 → $0.180 / $0.780 → $0.720cache read $0.006 → $0.0052026-09-17 18:50 UTC