Name: DeepSeek: R1 API
Brand: Deepseek
SKU: deepseek/deepseek-r1

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	lambda-ai	Direct host	$0.2	$0.6	—	-82.9% vs consensus	—	—	—	—
2	deepinfra	Direct host	$0.5	$2.15	$0.35	-38.6% vs consensus	—	—	—	—
3	openrouter → deepseek	Reseller	$0.5	$2.15	$0.35	-38.6% vs consensus	—	—	—	—
4	siliconflow	Direct host	$0.5	$2.18	—	-37.7% vs consensus	—	—	—	—
5	deepseek	Official	$0.55	$2.19	—	-37.4% vs consensus	—	—	—	—
6	vercel-ai-gateway → deepseek	Reseller	$0.55	$2.19	—	-37.4% vs consensus	—	—	—	—
7	gmi	Direct host	$0.57	$2.29	$0.23	-34.6% vs consensus	—	—	—	—
8	novita	Direct host	$0.7	$2.5	—	-28.6% vs consensus	1.4s	21.4 tps	—	—
9	openrouter → novita	Reseller	$0.7	$2.5	—	-28.6% vs consensus	—	—	—	—
10	hyperbolic	Direct host	$3	$3	—	-14.3% vs consensus	—	—	—	—
11	novita → deepseek	Reseller	$4	$4	—	+14.3% vs consensus	—	—	—	—
12	amazon-bedrock	Direct host	$1.35	$5.4	—	+54.3% vs consensus	1.1s	178.9 tps	—	—
13	google	Direct host	$1.35	$5.4	—	+54.3% vs consensus	1.1s	161.5 tps	—	—
14	google-vertex	Direct host	$1.35	$5.4	—	+54.3% vs consensus	—	—	—	—
15	wandb	Direct host	$1.35	$5.4	—	+54.3% vs consensus	—	—	—	—
16	azure → azure-ai	Reseller	$1.35	$5.4	—	+54.3% vs consensus	—	—	—	—
17	together	Direct host	$3	$7	—	+100.0% vs consensus	—	—	—	—
18	sambanova	Direct host	$5	$7	—	+100.0% vs consensus	—	—	—	—
19	fireworks	Direct host	$3	$8	—	+128.6% vs consensus	—	—	—	—
20	replicate	Direct host	$3.75	$10	—	+185.7% vs consensus	—	—	—	—
21	zeroeval → deepinfra Disabled by zeroeval · disabled	Reseller	$0.5	$2.15	—	-38.6% vs consensus	—	—	—	—
22	zeroeval → deepseek Disabled by zeroeval · disabled	Reseller	$0.55	$2.19	—	-37.4% vs consensus	—	—	—	—
23	zeroeval → novita Disabled by zeroeval · disabled	Reseller	$0.7	$2.5	—	-28.6% vs consensus	—	—	—	—
24	openrouter → azure Disabled by openrouter · disabled · unknown	Reseller	$1.49	$5.94	—	+69.7% vs consensus	—	—	—	—

#
1
Provider
lambda-ai
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.2
Output $ / 1M tokens
$0.6
Cache read $ / 1M tokens
—
-82.9% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
2
Provider
deepinfra
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2.15
Cache read $ / 1M tokens
$0.35
-38.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
3
Provider
openrouter → deepseek
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2.15
Cache read $ / 1M tokens
$0.35
-38.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
4
Provider
siliconflow
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2.18
Cache read $ / 1M tokens
—
-37.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
5
Provider
deepseek
Class
Official
$ / 1M tokens
Input $ / 1M tokens
$0.55
Output $ / 1M tokens
$2.19
Cache read $ / 1M tokens
—
-37.4% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
6
Provider
vercel-ai-gateway → deepseek
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.55
Output $ / 1M tokens
$2.19
Cache read $ / 1M tokens
—
-37.4% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
7
Provider
gmi
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.57
Output $ / 1M tokens
$2.29
Cache read $ / 1M tokens
$0.23
-34.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
8
Provider
novita
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$0.7
Output $ / 1M tokens
$2.5
Cache read $ / 1M tokens
—
-28.6% vs consensus
TTFT
1.4s
Throughput
21.4 tps
Uptime 24h
—
Requests 24h
—
#
9
Provider
openrouter → novita
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.7
Output $ / 1M tokens
$2.5
Cache read $ / 1M tokens
—
-28.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
10
Provider
hyperbolic
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$3
Output $ / 1M tokens
$3
Cache read $ / 1M tokens
—
-14.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
11
Provider
novita → deepseek
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$4
Output $ / 1M tokens
$4
Cache read $ / 1M tokens
—
+14.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
12
Provider
amazon-bedrock
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$1.35
Output $ / 1M tokens
$5.4
Cache read $ / 1M tokens
—
+54.3% vs consensus
TTFT
1.1s
Throughput
178.9 tps
Uptime 24h
—
Requests 24h
—
#
13
Provider
google
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$1.35
Output $ / 1M tokens
$5.4
Cache read $ / 1M tokens
—
+54.3% vs consensus
TTFT
1.1s
Throughput
161.5 tps
Uptime 24h
—
Requests 24h
—
#
14
Provider
google-vertex
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$1.35
Output $ / 1M tokens
$5.4
Cache read $ / 1M tokens
—
+54.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
15
Provider
wandb
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$1.35
Output $ / 1M tokens
$5.4
Cache read $ / 1M tokens
—
+54.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
16
Provider
azure → azure-ai
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$1.35
Output $ / 1M tokens
$5.4
Cache read $ / 1M tokens
—
+54.3% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
17
Provider
together
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$3
Output $ / 1M tokens
$7
Cache read $ / 1M tokens
—
+100.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
18
Provider
sambanova
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$5
Output $ / 1M tokens
$7
Cache read $ / 1M tokens
—
+100.0% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
19
Provider
fireworks
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$3
Output $ / 1M tokens
$8
Cache read $ / 1M tokens
—
+128.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
20
Provider
replicate
Class
Direct host
$ / 1M tokens
Input $ / 1M tokens
$3.75
Output $ / 1M tokens
$10
Cache read $ / 1M tokens
—
+185.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
21
Provider
zeroeval → deepinfra
Class
Reseller
Disabled by zeroeval · disabled
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2.15
Cache read $ / 1M tokens
—
-38.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
22
Provider
zeroeval → deepseek
Class
Reseller
Disabled by zeroeval · disabled
$ / 1M tokens
Input $ / 1M tokens
$0.55
Output $ / 1M tokens
$2.19
Cache read $ / 1M tokens
—
-37.4% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
23
Provider
zeroeval → novita
Class
Reseller
Disabled by zeroeval · disabled
$ / 1M tokens
Input $ / 1M tokens
$0.7
Output $ / 1M tokens
$2.5
Cache read $ / 1M tokens
—
-28.6% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
24
Provider
openrouter → azure
Class
Reseller
Disabled by openrouter · disabled · unknown
$ / 1M tokens
Input $ / 1M tokens
$1.49
Output $ / 1M tokens
$5.94
Cache read $ / 1M tokens
—
+69.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—

Source ecosystem

Loading…

DeepSeek: R1Reasoning

Best price — Output ($/1M tokens)

Best price — Output ($/1M tokens)

Markets