Skip to main content
DeepSeek serves its own DeepSeek models. Its API follows OpenAI’s format, so you wrap it with the OpenAI client and the SDK meters it with the OpenAI recipe.

Set up

Point the OpenAI client’s baseURL at DeepSeek and wrap it:

What is reported

DeepSeek returns a usage object in OpenAI’s format with the number of tokens each call consumed. The calls go through the OpenAI client, so they are reported under OpenAI event names. The wrapper reads the counts and reports them to Stigg as the metrics below. Chat Completions total_tokens includes the other token counts, so price the total or the parts, never both. To tell DeepSeek apart from other vendors on the same event name, add a dimension such as provider to the stiggContext. DeepSeek reports its cache usage in its own fields, prompt_cache_hit_tokens and prompt_cache_miss_tokens, rather than OpenAI’s cached_tokens. If the cached_tokens metric stays at zero for your DeepSeek traffic, build a meter on raw.prompt_cache_hit_tokens to meter cache hits. Every usage field the provider returns is also included, with a raw. prefix. See How usage is reported. For details on DeepSeek’s API, see DeepSeek’s API docs and context caching guide.