OpenAI o Series
A series of reasoning large models introduced by OpenAI that possess an internal chain of thought and excel at complex reasoning tasks, consuming additional thinking tokens for reasoning before producing output.
Core Facts
Reasoning models, represented by OpenAI o1, DeepSeek-R1, and QwQ, have chain-of-thought expansion as their core mechanism, generating a large number of intermediate reasoning steps before producing a final answer.
Reasoning models, represented by OpenAI's o series, DeepSeek-R1, and the Kimi K series, perform a chain-of-thought process before outputting, decomposing problems into multiple steps, performing self-verification, and deriving answers incrementally.
Timeline (last 90 days)
Reasoning tokens refer to the tokens consumed by the internal reasoning content generated by models with chain-of-thought capabilities (such as the OpenAI o series, DeepSeek-R1, etc.) before giving a final answer; they are usually not shown directly to the user but are counted toward billing and context window usage.
Thinking intensity (thinking intensity / reasoning effort) is a tunable parameter exposed to callers by some reasoning models (such as Claude 3.7 Sonnet and the OpenAI o series) to control the depth of the model's internal chain-of-thought reasoning and token consumption.
All Facts (4)
Reasoning models, represented by OpenAI o1, DeepSeek-R1, and QwQ, have chain-of-thought expansion as their core mechanism, generating a large number of intermediate reasoning steps before producing a final answer.
90%VerifiedReasoning models, represented by OpenAI's o series, DeepSeek-R1, and the Kimi K series, perform a chain-of-thought process before outputting, decomposing problems into multiple steps, performing self-verification, and deriving answers incrementally.
65%UnverifiedReasoning tokens refer to the tokens consumed by the internal reasoning content generated by models with chain-of-thought capabilities (such as the OpenAI o series, DeepSeek-R1, etc.) before giving a final answer; they are usually not shown directly to the user but are counted toward billing and context window usage.
50%UnverifiedThinking intensity (thinking intensity / reasoning effort) is a tunable parameter exposed to callers by some reasoning models (such as Claude 3.7 Sonnet and the OpenAI o series) to control the depth of the model's internal chain-of-thought reasoning and token consumption.
50%