How Claude Code token usage builds across a coding session

What normally enters the context

Typical inputs include system behavior, CLAUDE.md or project instructions, user messages, code excerpts, diffs, terminal output, MCP schemas and prior assistant actions. The exact composition depends on the current Claude Code version and integration, so provider-reported usage is more reliable than a simple character estimate.

How to audit a session

Choose one repeatable task. Record the initial context, each tool call, the number of turns and the final provider usage. Mark which content was unique, repeated, obsolete or unrelated. This creates a factual map of where tokens accumulate instead of blaming the model or one prompt.

What can be reduced safely

Varion keeps its proprietary engine implementation private. Commercial evaluation is based on measurable workload-specific outcomes, clear validation boundaries and customer-specific testing rather than disclosure of internal mechanisms. Use the dedicated Token Optimisation product area to evaluate whether the commercial result is suitable for your traffic; no universal performance percentage is promised.

Measurement checklist

1. Choose a representative completed task, not an artificial one-line prompt.
2. Record the selected model, provider input, cached input, output, retries and final result.
3. Change one optimization mechanism at a time so the cause remains visible.
4. Verify required identifiers, tool calls, code changes or business fields.
5. Keep passthrough available when the reduced request does not pass.

Varion commercial evaluation

Varion keeps proprietary product implementation details private. Evaluate Token Optimisation on representative traffic and judge it by the measured commercial result. New verified users receive 100,000 processed input tokens and 50 local test runs.