---
schema_version: "newruntime-agent-readable-v0.1"
type: "raw_signal"
id: "tg-2676"
slug: "claude-code-model-and-effort-are-separate-controls"
title: "Claude Code separates model choice from effort"
description: "Anthropic exposes model selection and effort level as different controls for capability, token use, latency, and persistence."
observed_at: "2026-07-13"
why_it_matters: "Agent routing is becoming a multidimensional runtime decision rather than a single model dropdown, making task-aware cost controls more practical."
novelty: "notable"
verification_level: "source-inspected"
signal_type: "field-report"
evidence_kind: "mixed"
status: "published"
telegram_message_id: 2676
telegram_url: "https://t.me/qwgai/2676"
topics: ["coding-agents","model-routing","agent-economics"]
entities: ["Claude Code","Anthropic"]
related_patterns: []
source_urls: ["https://claude.com/blog/claude-model-and-effort-level-in-claude-code","https://code.claude.com/docs/en/model-config"]
import_batch: "telegram-2026-07-17-v1"
routes: {"html":"https://newruntime.com/signals/claude-code-model-and-effort-are-separate-controls/","markdown":"https://newruntime.com/signals/claude-code-model-and-effort-are-separate-controls.md","json":"https://newruntime.com/signals/claude-code-model-and-effort-are-separate-controls.json"}
source_format: "telegram-export-normalized-json"
---

# Claude Code separates model choice from effort

## 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.

## Provenance

Normalized from QWG AI Telegram message 2676. The original Russian-language record remains available at https://t.me/qwgai/2676.