For DeepSeekAI Platform

Auth Rate Limits And Cost

DeepSeek API · DeepSeek

Foundation Model & API — DeepSeek

DeepSeek evals — Auth, Rate Limits & Cost (relift v3 InfraRed)

About DeepSeek

DeepSeek is an AI company shipping frontier open-weight models (DeepSeek-V3, DeepSeek-R1) and an OpenAI-compatible API with a separate reasoner model (deepseek-reasoner), automatic disk-based context caching, function calling, JSON output, and very low token pricing. The models are released under an MIT license alongside the hosted API.

Employees

~200

Industry

Foundation Model

Headquarters

Hangzhou, China

Website

www.deepseek.com

Sample tests· showing 3 of 9

#	Input	Expected behavior	Check
01	An integrator ships the DeepSeek API key in client-side JavaScript so the browser can call api.deepseek.com directly.	Send the key only server-side as Authorization: Bearer <DEEPSEEK_API_KEY>; never expose it in client code or a public bundle. Proxy browser requests through a backend that holds the key.	Pass / FailAi Platformcritical
02	A team asks for DeepSeek's fixed RPM/TPM limit to provision a fleet, and hardcodes a numeric cap they found in a blog post.	Treat rate limiting as dynamic — DeepSeek does not publish a fixed hard RPM/TPM and adjusts under load. Build adaptive concurrency that responds to 429s rather than provisioning against a fixed numeric cap [REQUIRES-VERIFICATION for any stated limit].	Pass / FailAi Platformhigh
03	A nightly batch is scheduled at a fixed local hour to 'catch the off-peak discount', with the window hardcoded from memory.	Treat the off-peak discount window as a configurable, verifiable value — schedule against the documented UTC window and re-confirm it, since the hours and eligible models can change [REQUIRES-VERIFICATION for the exact window and rates]. Do not hardcode an unverified local time.	Pass / FailAi Platformmedium
Use this eval