If you're routing through the OpenAI or Anthropic SDK, DeepSeek now lets you toggle chain-of-thoughtHaving a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.Full definition → on or off per request and dial reasoning effort (high/max), with the reasoning stream returned separately in `reasoning_content` so you can log or discard it without polluting the answer — plus 1M-tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → on the new v4-pro/flash tiers.
Terms in this piece · Glossary
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
