DeepSeek API pricing

8Models
14Providers
$0.06Lowest input, DeepSeek V4 Flash 0731
$0.18Lowest output, DeepSeek V4 Flash 0731

Providers

Munito AI

Price per model

Model	Lowest input	Lowest output	Lowest cached input	Context	Providers
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017	$0.09Sail Research	$0.30Sail Research	$0.003Doubleword	1.05M	6
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash	$0.12Morph	$0.42DeepInfra	$0.003Doubleword	1.05M	9
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp	$0.2156DeepInfra	$0.6468DeepInfra	$0.0069DeepInfra	1.05M	1
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813	$0.92Sail Research	$2.60DeepInfra	$0.04Nebius	1.05M	6
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731	$0.06DeepInfra	$0.18DeepInfra	$0.01Nebius	1.05M	9
DeepSeek V4 Flashdeepseek/deepseek-v4-flash	$0.14StreamLake	$0.28StreamLake	$0.0028Inference.net	1M	2
DeepSeek V4 Prodeepseek/deepseek-v4-pro	$1.30DeepInfra	$2.60DeepInfra	$0.0036Inference.net	1.05M	4
DeepSeek V3.2deepseek/deepseek-v3.2	$1.00Chutes	$1.00Chutes	$0.10Chutes	131K	2

USD per 1M tokens, as of November 5, 2026.

Price by provider

Model	DeepInfra	StreamLake	Doubleword	Inference.net	Nebius	Novita AI	Phala	Sail Research	Chutes	RunInfra	Wafer	Morph	Munito AI	Particle AI
DeepSeek V4.1 Flash 1017	–	–	$0.15 / $0.60	–	–	–	$0.75 / $1.60	$0.09 / $0.30	–	$0.15 / $0.60	$0.13 / $0.50	–	–	$0.2125 / $0.85
DeepSeek V4.1 Flash	$0.14 / $0.42	$0.30 / $1.20	$0.15 / $0.60	$0.30 / $1.00	$0.30 / $1.20	$0.30 / $1.20	–	–	–	$0.14 / $0.58	$0.19 / $0.65	$0.12 / $0.80	–	–
DeepSeek V4 Flash Vision Exp	$0.2156 / $0.6468	–	–	–	–	–	–	–	–	–	–	–	–	–
DeepSeek V4 Pro 0813	$1.30 / $2.60	$1.32 / $3.96	$1.32 / $3.96	–	$1.32 / $3.96	$1.32 / $3.96	–	$0.92 / $2.77	–	–	–	–	–	–
DeepSeek V4 Flash 0731	$0.06 / $0.18	$0.44 / $1.32	$0.09 / $0.18	$0.53 / $1.58	$0.14 / $0.28	–	$0.44 / $1.32	$0.09 / $0.18	$0.44 / $1.32	–	–	–	$0.099 / $0.25	–
DeepSeek V4 Flash	–	$0.14 / $0.28	–	$0.23 / $0.62	–	–	–	–	–	–	–	–	–	–
DeepSeek V4 Pro	$1.30 / $2.60	$1.74 / $3.48	–	$2.10 / $4.20	–	$1.60 / $3.20	–	–	–	–	–	–	–	–
DeepSeek V3.2	–	–	–	–	–	–	$1.00 / $1.00	–	$1.00 / $1.00	–	–	–	–	–

Input / output, USD per 1M tokens.

Cost

Model	1,000 chat replies2K in, 500 out each	1,000 agent tasks50K in, 5K out each	Monthly batch job500M in, 50M out
DeepSeek V4.1 Flash 1017Sail Research	$0.33	$6.00	$60.00
DeepSeek V4.1 FlashDeepInfra	$0.49	$9.10	$91.00
DeepSeek V4 Flash Vision ExpDeepInfra	$0.75	$14.01	$140.14
DeepSeek V4 Pro 0813Sail Research	$3.23	$59.85	$598.50
DeepSeek V4 Flash 0731DeepInfra	$0.21	$3.90	$39.00
DeepSeek V4 FlashStreamLake	$0.42	$8.40	$84.00
DeepSeek V4 ProDeepInfra	$3.90	$78.00	$780.00
DeepSeek V3.2Chutes	$2.50	$55.00	$550.00

On each model's cheapest provider by input plus output list price.

FAQ

How much does the DeepSeek API cost?

Across the 8 DeepSeek models on RouterPlus, the lowest listed input price runs from $0.06 to $1.30 per million tokens, and output from $0.18 to $2.60. Prices as of November 5, 2026.

What is the cheapest DeepSeek model?

DeepSeek V4 Flash 0731, at $0.06 per million input tokens and $0.18 per million output tokens on DeepInfra.

Which provider has the lowest DeepSeek prices?

DeepInfra lists the lowest input price on 3 of 8 DeepSeek models. The table above shows every provider's price for each model.

Does the DeepSeek API have cached input pricing?

Yes, on 8 of 8 models. The lowest cached input rate is $0.0028 per million tokens (DeepSeek V4 Flash).

How does RouterPlus bill DeepSeek usage?

Calls draw on prepaid credits at the listed rate of the provider that serves them. One key covers every DeepSeek model and provider.

Run DeepSeek in production

Open in console I need inference