Name: DeepSeek: DeepSeek V4 Flash API
Brand: Deepseek
SKU: deepseek/deepseek-v4-flash

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

#	Provider	Class	Input $/M	Output $/M	Cache ($/M Read)	vs consensus	TTFT	Throughput	Uptime 24h	Requests 24h
1	bitdeer	Direct host	$0.04	$0.08	—	-70.0% vs consensus	1.5s	138.0 tps	—	—
2	openrouter → streamlake	Reseller	$0.07	$0.13	$0.01	-52.3% vs consensus	—	—	—	—
3	openrouter → baidu	Reseller	$0.07	$0.13	$0.01	-52.2% vs consensus	—	—	—	—
4	openrouter → digitalocean	Reseller	$0.07	$0.17	$0.02	-40.0% vs consensus	—	—	—	—
5	openrouter → deepseek	Reseller	$0.09	$0.18	$0.02	-36.7% vs consensus	—	—	—	—
6	deepinfra	Direct host	$0.08	$0.18	$0.02	-35.7% vs consensus	1.4s reasoning 1.1s	37.3 tps	—	—
7	openrouter → deepinfra	Reseller	$0.09	$0.18	$0.02	-35.7% vs consensus	—	—	—	—
8	gmi	Direct host	$0.09	$0.18	$0.02	-35.0% vs consensus	2.9s reasoning 12.8s	112.8 tps	—	—
9	openrouter → gmicloud	Reseller	$0.09	$0.18	$0.02	-35.0% vs consensus	—	—	—	—
10	makora	Direct host	$0.09	$0.2	—	-30.4% vs consensus	1.2s reasoning 711ms	72.3 tps	—	—
11	openrouter → wafer	Reseller	$0.1	$0.25	$0.05	-10.7% vs consensus	—	—	—	—
12	digitalocean	Direct host	$0.08	$0.25	—	-10.0% vs consensus	1.1s	31.0 tps	—	—
13	baseten	Direct host	$0.13	$0.26	—	-7.1% vs consensus	4.9s	112.4 tps	—	—
14	openrouter → qwen	Reseller	$0.13	$0.27	$0.03	-4.3% vs consensus	—	—	—	—
15	openrouter → venice	Reseller	$0.14	$0.28	$0.03	-1.8% vs consensus	—	—	—	—
16	siliconflow	Direct host	$0.13	$0.28	$0.03	+0.0% vs consensus	1.2s reasoning 1.7s	123.3 tps	—	—
17	openrouter → siliconflow	Reseller	$0.13	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
18	coreweave	Direct host	$0.14	$0.28	—	+0.0% vs consensus	1.6s reasoning 2.0s	77.4 tps	—	—
19	crusoe	Direct host	$0.14	$0.28	—	+0.0% vs consensus	1.0s	293.8 tps	—	—
20	fireworks	Direct host	$0.14	$0.28	$0.03	+0.0% vs consensus	603ms	254.2 tps	—	—
21	nebius	Direct host	$0.14	$0.28	—	+0.0% vs consensus	2.2s	226.9 tps	—	—
22	novita	Direct host	$0.14	$0.28	—	+0.0% vs consensus	2.0s reasoning 1.9s	115.2 tps	—	—
23	parasail	Direct host	$0.14	$0.28	—	+0.0% vs consensus	1.7s reasoning 1.4s	63.9 tps	—	—
24	wandb	Direct host	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
25	novita → deepseek	Reseller	$0.14	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
26	openrouter → atlas-cloud	Reseller	$0.14	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
27	openrouter → novita	Reseller	$0.14	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
28	openrouter → parasail	Reseller	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
29	openrouter → nextbit	Reseller	$0.15	$0.35	$0.04	+25.0% vs consensus	—	—	—	—
30	dashscope	Direct host	$0.2	$0.4	$0.04	+42.9% vs consensus	—	—	—	—
31	openrouter → phala	Reseller	$0.2	$0.4	$0.07	+42.9% vs consensus	—	—	—	—
32	openrouter → mancer	Reseller	$0.19	$0.5	—	+78.6% vs consensus	—	—	—	—
33	azure → azure-ai	Reseller	$0.19	$0.51	$0.02	+82.1% vs consensus	—	—	—	—
34	openrouter → azure	Reseller	$0.21	$0.56	$0.03	+100.0% vs consensus	—	—	—	—
35	wafer	Direct host	$0.28	$0.56	—	+100.0% vs consensus	787ms	135.5 tps	—	—
36	deepseek	Official	$0.3	$1.2	$0.01	+328.6% vs consensus	1.2s reasoning 1.3s	113.1 tps	—	—
37	openrouter → open-inference Disabled by openrouter · disabled · fp8	Reseller	$0.07	$0.18	$0.03	-35.7% vs consensus	—	—	—	—
38	openrouter → dekallm Disabled by openrouter · disabled · unknown	Reseller	$0.09	$0.18	$0.02	-35.7% vs consensus	—	—	—	—
39	openrouter → sail-research Disabled by openrouter · disabled · fp4	Reseller	$0.09	$0.18	$0.02	-35.7% vs consensus	—	—	—	—
40	openrouter → akashml Disabled by openrouter · disabled · fp8	Reseller	$0.1	$0.2	$0.01	-30.0% vs consensus	—	—	—	—
41	openrouter → io-net Disabled by openrouter · disabled · fp8	Reseller	$0.14	$0.28	$0.07	-0.7% vs consensus	—	—	—	—
42	openrouter → morph Disabled by openrouter · disabled · unknown	Reseller	$0.14	$0.28	$0.07	-0.7% vs consensus	—	—	—	—
43	openrouter → ambient Disabled by openrouter · disabled · fp4	Reseller	$0.14	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
44	openrouter → coreweave Disabled by openrouter · disabled · fp8	Reseller	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
45	openrouter → fireworks Disabled by openrouter · disabled · unknown	Reseller	$0.14	$0.28	$0.03	+0.0% vs consensus	—	—	—	—
46	openrouter → ionstream Disabled by openrouter · disabled · fp4	Reseller	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
47	openrouter → wandb Disabled by openrouter · disabled · fp8	Reseller	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
48	openrouter → wandb-legacy Disabled by openrouter · disabled · fp8	Reseller	$0.14	$0.28	$0.07	+0.0% vs consensus	—	—	—	—
49	openrouter → cloudflare Disabled by openrouter · disabled · unknown	Reseller	$0.44	$1.32	$0.01	+371.4% vs consensus	—	—	—	—

#
1
Provider
bitdeer
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.04
Output $ / 1M tokens
$0.08
Cache read $ / 1M tokens
—
-70.0% vs consensus
TTFT
1.5s
Throughput
138.0 tps
Uptime 24h
—
Requests 24h
—
#
2
Provider
openrouter → streamlake
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.07
Output $ / 1M tokens
$0.13
Cache read $ / 1M tokens
$0.01
-52.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
3
Provider
openrouter → baidu
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.07
Output $ / 1M tokens
$0.13
Cache read $ / 1M tokens
$0.01
-52.2% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
4
Provider
openrouter → digitalocean
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.07
Output $ / 1M tokens
$0.17
Cache read $ / 1M tokens
$0.02
-40.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
5
Provider
openrouter → deepseek
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-36.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
6
Provider
deepinfra
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.08
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.7% vs consensus
TTFT
1.4s
reasoning 1.1s
Throughput
37.3 tps
Uptime 24h
—
Requests 24h
—
#
7
Provider
openrouter → deepinfra
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
8
Provider
gmi
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.0% vs consensus
TTFT
2.9s
reasoning 12.8s
Throughput
112.8 tps
Uptime 24h
—
Requests 24h
—
#
9
Provider
openrouter → gmicloud
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
10
Provider
makora
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.2
Cache read $ / 1M tokens
—
-30.4% vs consensus
TTFT
1.2s
reasoning 711ms
Throughput
72.3 tps
Uptime 24h
—
Requests 24h
—
#
11
Provider
openrouter → wafer
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.1
Output $ / 1M tokens
$0.25
Cache read $ / 1M tokens
$0.05
-10.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
12
Provider
digitalocean
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.08
Output $ / 1M tokens
$0.25
Cache read $ / 1M tokens
—
-10.0% vs consensus
TTFT
1.1s
Throughput
31.0 tps
Uptime 24h
—
Requests 24h
—
#
13
Provider
baseten
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.13
Output $ / 1M tokens
$0.26
Cache read $ / 1M tokens
—
-7.1% vs consensus
TTFT
4.9s
Throughput
112.4 tps
Uptime 24h
—
Requests 24h
—
#
14
Provider
openrouter → qwen
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.13
Output $ / 1M tokens
$0.27
Cache read $ / 1M tokens
$0.03
-4.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
15
Provider
openrouter → venice
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
-1.8% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
16
Provider
siliconflow
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.13
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
1.2s
reasoning 1.7s
Throughput
123.3 tps
Uptime 24h
—
Requests 24h
—
#
17
Provider
openrouter → siliconflow
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.13
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
18
Provider
coreweave
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
—
+0.0% vs consensus
TTFT
1.6s
reasoning 2.0s
Throughput
77.4 tps
Uptime 24h
—
Requests 24h
—
#
19
Provider
crusoe
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
—
+0.0% vs consensus
TTFT
1.0s
Throughput
293.8 tps
Uptime 24h
—
Requests 24h
—
#
20
Provider
fireworks
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
603ms
Throughput
254.2 tps
Uptime 24h
—
Requests 24h
—
#
21
Provider
nebius
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
—
+0.0% vs consensus
TTFT
2.2s
Throughput
226.9 tps
Uptime 24h
—
Requests 24h
—
#
22
Provider
novita
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
—
+0.0% vs consensus
TTFT
2.0s
reasoning 1.9s
Throughput
115.2 tps
Uptime 24h
—
Requests 24h
—
#
23
Provider
parasail
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
—
+0.0% vs consensus
TTFT
1.7s
reasoning 1.4s
Throughput
63.9 tps
Uptime 24h
—
Requests 24h
—
#
24
Provider
wandb
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
25
Provider
novita → deepseek
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
26
Provider
openrouter → atlas-cloud
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
27
Provider
openrouter → novita
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
28
Provider
openrouter → parasail
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
29
Provider
openrouter → nextbit
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.15
Output $ / 1M tokens
$0.35
Cache read $ / 1M tokens
$0.04
+25.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
30
Provider
dashscope
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.2
Output $ / 1M tokens
$0.4
Cache read $ / 1M tokens
$0.04
+42.9% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
31
Provider
openrouter → phala
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.2
Output $ / 1M tokens
$0.4
Cache read $ / 1M tokens
$0.07
+42.9% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
32
Provider
openrouter → mancer
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.19
Output $ / 1M tokens
$0.5
Cache read $ / 1M tokens
—
+78.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
33
Provider
azure → azure-ai
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.19
Output $ / 1M tokens
$0.51
Cache read $ / 1M tokens
$0.02
+82.1% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
34
Provider
openrouter → azure
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.21
Output $ / 1M tokens
$0.56
Cache read $ / 1M tokens
$0.03
+100.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
35
Provider
wafer
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.28
Output $ / 1M tokens
$0.56
Cache read $ / 1M tokens
—
+100.0% vs consensus
TTFT
787ms
Throughput
135.5 tps
Uptime 24h
—
Requests 24h
—
#
36
Provider
deepseek
Class
Official
$ / 1M tokens
Input $ / 1M tokens
$0.3
Output $ / 1M tokens
$1.2
Cache read $ / 1M tokens
$0.01
+328.6% vs consensus
TTFT
1.2s
reasoning 1.3s
Throughput
113.1 tps
Uptime 24h
—
Requests 24h
—
#
37
Provider
openrouter → open-inference
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.07
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.03
-35.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
38
Provider
openrouter → dekallm
Class
Reseller
Disabled by openrouter · disabled · unknown
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
39
Provider
openrouter → sail-research
Class
Reseller
Disabled by openrouter · disabled · fp4
$ / 1M tokens
Input $ / 1M tokens
$0.09
Output $ / 1M tokens
$0.18
Cache read $ / 1M tokens
$0.02
-35.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
40
Provider
openrouter → akashml
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.1
Output $ / 1M tokens
$0.2
Cache read $ / 1M tokens
$0.01
-30.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
41
Provider
openrouter → io-net
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
-0.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
42
Provider
openrouter → morph
Class
Reseller
Disabled by openrouter · disabled · unknown
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
-0.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
43
Provider
openrouter → ambient
Class
Reseller
Disabled by openrouter · disabled · fp4
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
44
Provider
openrouter → coreweave
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
45
Provider
openrouter → fireworks
Class
Reseller
Disabled by openrouter · disabled · unknown
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.03
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
46
Provider
openrouter → ionstream
Class
Reseller
Disabled by openrouter · disabled · fp4
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
47
Provider
openrouter → wandb
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
48
Provider
openrouter → wandb-legacy
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.14
Output $ / 1M tokens
$0.28
Cache read $ / 1M tokens
$0.07
+0.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
49
Provider
openrouter → cloudflare
Class
Reseller
Disabled by openrouter · disabled · unknown
$ / 1M tokens
Input $ / 1M tokens
$0.44
Output $ / 1M tokens
$1.32
Cache read $ / 1M tokens
$0.01
+371.4% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—

Source ecosystem

Loading…

DeepSeek: DeepSeek V4 FlashReasoning

Best price — Output ($/1M tokens)

Best price — Output ($/1M tokens)

Markets