DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017InputOutput

Compare its 12 providers Incident RSSCompare with DeepSeek V4.1 Flash, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423

CompareDeepSeek V4.1 Flash 1017

	State
BaseTenbaseten	Healthy	100%	100%	100%	100%	312ms	5.60s	312 tps	1.0M	$0.300 / $1.20
Cloudflarecloudflare	Healthy	100%	98.52%	100%	100%	2.22s	32.1s	84 tps	1.0M	$0.100 / $0.600
DeepInfradeepinfra/fp8fp8	Healthy	100%	98.54%	100%	100%	695ms	4.22s	99 tps	1.0M	$0.098 / $0.294
DeepInfradeepinfra/fp8/flexfp8	Healthy	100%	95.29%	100%	100%	4.42s	18.0s	64 tps	1.0M	$0.078 / $0.235
DeepInfradeepinfra/fp8/priorityfp8	Healthy	100%	98.05%	100%	100%	1.06s	6.18s	138 tps	1.0M	$0.147 / $0.441
DeepSeekdeepseek	Healthy	100%	100%	100%	100%	1.00s	2.98s	50 tps	1.0M	$0.150 / $0.600
Fireworksfireworks	Healthy	100%	100%	100%	100%	585ms	11.0s	141 tps	1.0M	$0.300 / $1.20
InferenceNetinference-net/fp8fp8	Healthy	100%	100%	100%	100%	435ms	4.45s	168 tps	262K	$0.080 / $0.500
Parasailparasail/fp8fp8	Healthy	100%	100%	100%	100%	880ms	15.8s	137 tps	1.0M	$0.300 / $1.20
PrimeIntellectprimeintellect	Healthy	100%	99.33%	99.05%	99.05%	1.30s	20.8s	124 tps	1.0M	$0.300 / $1.20
Relacerelace	Healthy	100%	100%	100%	100%	1.02s	5.88s	130 tps	1.0M	$0.050 / $0.600
Morphmorph/fp8fp8	No data	—	—	100%	100%	—	—	—	1.0M	$0.081 / $0.550

BaseTen100%
Healthy24h 100%
7d
100%
30d
100%
p50
312ms
p99
5.60s
Throughput
312 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
baseten
Cloudflare100%
Healthy24h 98.52%
7d
100%
30d
100%
p50
2.22s
p99
32.1s
Throughput
84 tps
Context
1.0M
$/Mtok
$0.100 / $0.600
cloudflare
DeepInfra100%
Healthy24h 98.54%
7d
100%
30d
100%
p50
695ms
p99
4.22s
Throughput
99 tps
Context
1.0M
$/Mtok
$0.098 / $0.294
deepinfra/fp8fp8
DeepInfra100%
Healthy24h 95.29%
7d
100%
30d
100%
p50
4.42s
p99
18.0s
Throughput
64 tps
Context
1.0M
$/Mtok
$0.078 / $0.235
deepinfra/fp8/flexfp8
DeepInfra100%
Healthy24h 98.05%
7d
100%
30d
100%
p50
1.06s
p99
6.18s
Throughput
138 tps
Context
1.0M
$/Mtok
$0.147 / $0.441
deepinfra/fp8/priorityfp8
DeepSeek100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.00s
p99
2.98s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.150 / $0.600
deepseek
Fireworks100%
Healthy24h 100%
7d
100%
30d
100%
p50
585ms
p99
11.0s
Throughput
141 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
fireworks
InferenceNet100%
Healthy24h 100%
7d
100%
30d
100%
p50
435ms
p99
4.45s
Throughput
168 tps
Context
262K
$/Mtok
$0.080 / $0.500
inference-net/fp8fp8
Parasail100%
Healthy24h 100%
7d
100%
30d
100%
p50
880ms
p99
15.8s
Throughput
137 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
parasail/fp8fp8
PrimeIntellect100%
Healthy24h 99.33%
7d
99.05%
30d
99.05%
p50
1.30s
p99
20.8s
Throughput
124 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
primeintellect
Relace100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.02s
p99
5.88s
Throughput
130 tps
Context
1.0M
$/Mtok
$0.050 / $0.600
relace
Morph—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.081 / $0.550
morph/fp8fp8

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

History

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.

Jul

Aug

Sep

Oct

deepinfra/fp8/priority

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 12 endpoints · 1 day with data, 1 endpoint-day below 90%.

Price changes

DeepSeek V4.1 Flash 1017 Relacerelace$0.200 → $0.050 / $0.6002026-10-18 04:05 UTC