Pricing / DeepSeek

DeepSeek API pricing

6 model entries. DeepSeek entries in the bundled pricing snapshot. Source rate fields are shown as encoded in the snapshot dated 2026-03-25; model modality is not encoded.

Lowest encoded input rate

$0.14/1M

deepseek-coder

Highest encoded input rate

$0.55/1M

deepseek-r1

Models with cache pricing

4 of 6

Interpret the /1M columns as token rates only for models independently verified as token-billed. Non-text billing units are not represented in this snapshot schema.

ModelInput $/1MOutput $/1MCache $/1M
deepseek-coder$0.14$0.28-
deepseek-v3$0.27$1.1$0.07
deepseek-chat$0.28$0.42$0.028
deepseek-reasoner$0.28$0.42$0.028
deepseek-v3.2$0.28$0.42$0.028
deepseek-r1$0.55$2.19-

Use the DeepSeek snapshot as a reference, then measure the request

Local tracking can estimate supported responses from provider usage fields. The authenticated gateway path adds request identity, persisted cost evidence, session attribution, and pre-dispatch budget checks.