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%	294ms	5.48s	331 tps	1.0M	$0.300 / $1.20
Cloudflarecloudflare	Healthy	100%	98.43%	100%	100%	2.28s	31.9s	81 tps	1.0M	$0.100 / $0.600
DeepInfradeepinfra/fp8fp8	Healthy	100%	98.46%	100%	100%	641ms	5.08s	126 tps	1.0M	$0.098 / $0.294
DeepInfradeepinfra/fp8/flexfp8	Healthy	100%	94.93%	100%	100%	2.33s	10.5s	92 tps	1.0M	$0.078 / $0.235
DeepInfradeepinfra/fp8/priorityfp8	Healthy	100%	97.95%	100%	100%	934ms	8.60s	128 tps	1.0M	$0.147 / $0.441
DeepSeekdeepseek	Healthy	100%	100%	100%	100%	915ms	2.28s	52 tps	1.0M	$0.150 / $0.600
Fireworksfireworks	Healthy	100%	100%	100%	100%	509ms	5.44s	172 tps	1.0M	$0.300 / $1.20
InferenceNetinference-net/fp8fp8	Healthy	100%	100%	100%	100%	366ms	4.49s	163 tps	262K	$0.080 / $0.500
Parasailparasail/fp8fp8	Healthy	100%	100%	100%	100%	877ms	16.1s	127 tps	1.0M	$0.300 / $1.20
PrimeIntellectprimeintellect	Healthy	100%	98.95%	100%	100%	1.30s	20.5s	117 tps	1.0M	$0.300 / $1.20
Relacerelace	Healthy	100%	100%	100%	100%	1.09s	6.92s	124 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
294ms
p99
5.48s
Throughput
331 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
baseten
Cloudflare100%
Healthy24h 98.43%
7d
100%
30d
100%
p50
2.28s
p99
31.9s
Throughput
81 tps
Context
1.0M
$/Mtok
$0.100 / $0.600
cloudflare
DeepInfra100%
Healthy24h 98.46%
7d
100%
30d
100%
p50
641ms
p99
5.08s
Throughput
126 tps
Context
1.0M
$/Mtok
$0.098 / $0.294
deepinfra/fp8fp8
DeepInfra100%
Healthy24h 94.93%
7d
100%
30d
100%
p50
2.33s
p99
10.5s
Throughput
92 tps
Context
1.0M
$/Mtok
$0.078 / $0.235
deepinfra/fp8/flexfp8
DeepInfra100%
Healthy24h 97.95%
7d
100%
30d
100%
p50
934ms
p99
8.60s
Throughput
128 tps
Context
1.0M
$/Mtok
$0.147 / $0.441
deepinfra/fp8/priorityfp8
DeepSeek100%
Healthy24h 100%
7d
100%
30d
100%
p50
915ms
p99
2.28s
Throughput
52 tps
Context
1.0M
$/Mtok
$0.150 / $0.600
deepseek
Fireworks100%
Healthy24h 100%
7d
100%
30d
100%
p50
509ms
p99
5.44s
Throughput
172 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
fireworks
InferenceNet100%
Healthy24h 100%
7d
100%
30d
100%
p50
366ms
p99
4.49s
Throughput
163 tps
Context
262K
$/Mtok
$0.080 / $0.500
inference-net/fp8fp8
Parasail100%
Healthy24h 100%
7d
100%
30d
100%
p50
877ms
p99
16.1s
Throughput
127 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
parasail/fp8fp8
PrimeIntellect100%
Healthy24h 98.95%
7d
100%
30d
100%
p50
1.30s
p99
20.5s
Throughput
117 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
primeintellect
Relace100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.09s
p99
6.92s
Throughput
124 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 1m 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.

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