DeepSeek Chat API pricing

Prices last checked: 28 Oct 2026 LLMs
$ per 1M input $0.280
$ per 1M output $0.420

Standard tier, blended at 3:1 input to output: $0.315 per million tokens.

DeepSeek charges $0.280 per million input tokens and $0.420 per million output tokens for DeepSeek Chat. It is sold in 2 forms, from $0.315 to $0.450 blended; the table below shows what each costs against standard. 5 of the models nearest it in price are cheaper on a blended basis.

$0.280
$/1M input
$0.420
$/1M output
$0.028
$/1M cached in
131,072
Context window
$24.36
1k req/day, monthly

Every tier of DeepSeek Chat

Blended at 3:1 input to output. The last column compares each against the standard tier.

DeepSeek Chat tiers, snapshots and resellers, checked 28 Oct 2026
Source
Standard Standard deepseek-chat DeepSeek $0.280 $0.420 $0.028 $0.315 Standard ↗
Standard deepseek-chat OpenRouter $0.257 $1.03 Not listed $0.450 +43% ↗

Prices last checked: . Methodology

Which tier to use

What each costs against standard in our data, and the job it is for.

Direct or through a reseller

Through OpenRouter, deepseek-chat is 43% more than buying direct. A reseller is worth it for one bill across vendors and automatic fallback; buy direct for the vendor's own batch, caching and rate-limit terms.

Against the models nearest in price

Standard tiers, blended at a 3:1 input to output ratio.

Calculator →
DeepSeek Chat against comparable models, checked 28 Oct 2026
Source
DeepSeek Chat This model DeepSeek $0.280 $0.420 131,072 $0.315 ↗

Prices last checked: . Methodology

Questions

How much does DeepSeek Chat cost per million tokens?

$0.280 per million input tokens and $0.420 per million output tokens, with cached input at $0.028. At a 3:1 input to output mix that blends to $0.315. Checked 28 Oct 2026.

What would DeepSeek Chat cost for a real workload?

A thousand requests a day at 2,000 input and 600 output tokens each comes to $24.36 a month on the standard tier.

What is the context window for DeepSeek Chat?

131,072 tokens of input, with up to 8,192 tokens of output.

DeepSeek Reasoner · DeepSeek V3.2 · Llama 4 Maverick · GPT-4o mini · Llama 3.1 70B Instruct · All DeepSeek models · Cost calculator