DeepSeek token usage refers to the actual input and output tokens recorded by the API for each request, and these values are the only source of truth for billing. Unlike rough character-based estimates, real cost is calculated directly from the…
Quick answer: DeepSeek Tool Calls let the model request external functions during a chat workflow, but your application executes them. As of April 5, 2026, both deepseek-chat and deepseek-reasoner support Tool Calls on DeepSeek-V3.2 with a 128K context window. In…
DeepSeek Context Caching is a built-in API feature that automatically reuses repeated prompt prefixes across requests. It does not store memory or conversations. Instead, it reduces input cost and latency when you resend the same front-loaded context. Last verified: April…
Last verified: April 4, 2026 DeepSeek Thinking Mode is not just a prompt style. In the current API, it is a distinct execution mode that changes output structure, feature support, and some parameter behavior. You can enable it either by…
DeepSeek error codes are much easier to fix when you separate request-side problems from server-side problems first. The current official DeepSeek error-code list centers on seven main HTTP responses: 400, 401, 402, 422, 429, 500, and 503. The current API…
Quickstart (5–10 Minutes) The DeepSeek API is largely compatible with OpenAI’s API format. This means you can use familiar tools and libraries (like OpenAI’s SDK) by pointing them to DeepSeek’s endpoints. To get started, you will need to obtain an…