Inference
Thinking Tokens
The tokens a reasoning model generates while working through a problem before it writes its final answer.
In depth
The tokens a reasoning model generates while working through a problem before it writes its final answer. OpenAI calls them reasoning tokens and Anthropic calls them thinking tokens, and both bill them as output tokens even when the raw reasoning is hidden or only shown as a summary. They also take up space in the context window. This is why the same prompt can cost several times more at a higher effort level with no change in the visible answer length.
Primary source: platform.claude.com
Example
In practice, developers reach for Thinking Tokens when they need the capability described above as part of an AI feature or workflow.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Inference.
FAQ
Common questions
What is Thinking Tokens?
The tokens a reasoning model generates while working through a problem before it writes its final answer.
Why does Thinking Tokens matter for AI developers?
Thinking Tokens sits in the Inference part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Thinking Tokens?
Developers Digest publishes tutorials and videos that cover Inference topics including Thinking Tokens. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
Inference
Input vs Output Token Pricing
The split pricing model where LLM APIs charge one rate per million tokens you send (input) and a higher rate per million tokens the model generates (output).
Inference
Reasoning Effort
An API setting that tells a reasoning model how much work to put into a response, trading answer quality against latency and token cost.
Inference
Test-Time Compute
The computation a model spends while answering a prompt, as opposed to the compute spent training it.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever