Normalized Telegram record
Claude Code separates model choice from effort
Anthropic exposes model selection and effort level as different controls for capability, token use, latency, and persistence.
Signal contract
Anthropic exposes model selection and effort level as different controls for capability, token use, latency, and persistence. Agent routing is becoming a multidimensional runtime decision rather than a single model dropdown, making task-aware cost controls more practical. Novelty: notable. Verification: source-inspected. This New Runtime record is an evidence-linked retrieval unit.
Source ledger
Publishable sources attached to this record.
| # | Source | Role | Public status |
|---|---|---|---|
| 1 | claude.comsource | primary receipt | source_urls |
| 2 | code.claude.comsource | supporting receipt | source_urls |
Observation
Anthropic exposes model selection and effort level as different controls for capability, token use, latency, and persistence.
Why it matters
Agent routing is becoming a multidimensional runtime decision rather than a single model dropdown, making task-aware cost controls more practical.
Entities
Claude Code, Anthropic
Provenance
This public record is an English normalization of QWG AI Telegram message 2676. The complete original-language post remains the canonical raw message.