The chat/completions Mystery
It's clearly a conversation — so why is the API called "completions"? A typewriter animation explains
THE QUESTION THIS PAGE ANSWERS
ANSWER FIRSTWhat is the key idea behind “The chat/completions Mystery”?
It's clearly a conversation — so why is the API called "completions"? A typewriter animation explains
Make the claim earn its place. Use this page as a decision aid, not a definition to memorize. Connect the idea to one real task, one observable result, and one failure that would change your mind.
Write one question you could answer with evidence after trying this idea.
A conclusion that sounds complete but leaves the key assumption untested.
It's clearly a "chat" — so why is it called "completions"?
Two companies, two very different naming choices — each reflecting a different understanding of what LLMs fundamentally are.
[user] Who is Zixia Fairy? (紫霞仙子)
[assistant]
shaped the entire world.
/chat/completions was the paradigm that first ignited the marketHow “An Interesting Question” changes an answer
“It's clearly a "chat" — so why is it called " completions "” shows that a model does not process the “word count” we see. It processes Token pieces. Tokenization affects input length, how much context fits, and how much computation a request consumes.
Length, information, and context are different
As “Two companies, two very different naming choices — each reflecting a different understanding of what LLMs fundamentally are” grows, separate three questions: how many Tokens the text becomes, which pieces can change the current decision, and whether older material has fallen outside the context window. Removing repetition is often more useful than simply making the window larger.
Keep what can change the decision
Use “Two companies, two very different naming choices — each reflecting a different understanding of what LLMs fundamentally are” as an A/B test: keep the same question while removing repeated background, compressing format, and trimming irrelevant history. Compare answer quality, latency, and Token count.
From “An Interesting Question” to “Viewing a Conversation Through the Completions Lens”
“An Interesting Question” grounds the problem in “It's clearly a "chat" — so why is it called " completions "”. “Viewing a Conversation Through the Completions Lens” then moves it toward “↺ Replay What the model actually "sees" (the assembled text) [system] You are a helpful assistant. [user] Who is Zixia Fairy? (紫霞仙子) [assistant] What the Model Does After the [assistant] marker, it predicts the…”. Together, they show that the lesson is not just a conclusion to remember, but a claim with conditions.
Carry the judgment into the next situation
For long text, keep what can change the conclusion before compressing format and history. A larger context is worth its cost only when the added information is useful.
- “An Interesting Question”: It's clearly a "chat" — so why is it called " completions "
- “Viewing a Conversation Through the Completions Lens”: ↺ Replay What the model actually "sees" (the assembled text) [system] You are a helpful assistant. [user] Who is Zixia Fairy? (紫霞仙子) [assistant] What the Model Does After the [assistant] marker, it predicts the…
- “The closing point”: Two companies, two very different naming choices — each reflecting a different understanding of what LLMs fundamentally are
The final “The closing point” brings the discussion to “Two companies, two very different naming choices — each reflecting a different understanding of what LLMs fundamentally are”. The useful thing to carry forward is knowing which judgments must be revisited when input, scale, or risk changes.
I turned one judgment from this article into a small experiment I could run today. Knowing what to observe next is more useful than simply remembering the conclusion.
After reading this, I first looked for the conditions behind the idea instead of copying the method into a project. That order made the later trade-offs much clearer.
When this judgment reaches real work, which constraint should be added first? I am curious which step matters most between reading and the first practical attempt.
No discussion on this article yet.