Model Provider Request
Permintaan ke Penyedia Model
One round-trip from the harness to the model provider. The unit that tokens are billed on.
A model provider request is one round-trip from the harness to the provider. The harness sends the current context; the provider returns one response, which is either a tool call or a final answer. A single user message can spawn many requests if the agent calls tools, because each tool result triggers another one.
Each request carries everything: the system prompt, the full conversation so far, every tool result. The model is stateless, so the provider keeps nothing between requests. Request forty re-sends what request thirty-nine sent, plus one more tool result. The prefix cache exists to make that repetition affordable.
The request is also the unit of billing. Input tokens, output tokens, and cache discounts are all counted per request, which is why an innocuous-looking question can cost a surprise: the cost is proportional to the number of requests times the size of the context each one carries. When you wonder where the tokens went, count the requests, not the turns.
Related terms
Input Tokens
Tokens the harness sends on each request. Billed at a lower rate than output tokens.
Output Tokens
Tokens the model generates back. Billed at a higher rate, because generating costs more than reading.
Prefix Cache
The provider-side store that lets consecutive requests skip re-processing a shared prefix.
Context
The relevant information the agent has access to right now. A measure of quality, not quantity.
Agent Loop
The repeated cycle of decide, act, observe. Where autonomy actually comes from.
Want this working inside your team?
It starts with one conversation about your workflow.