Choosing the right Claude tier for each role in an agent workflow - orchestrator, default, and parallel worker - by the job and the token bill, not the benchmark.
Fable 5 escalates for the hardest reasoning, Opus 5 orchestrates near Fable at half the price, Sonnet 5 is the default worker, Haiku 4.5 does the parallel grunt work. Choose by the job and the token bill, not the benchmark.
Sonnet 5 ships as the default on Free and Pro with intro API pricing at $2/$10 per million tokens - near Opus 5 on agentic benchmarks at 40% of Opus input cost through the 2026-08-31 intro window (60% at standard pricing) when you keep effort at Medium or below.
Fable 5 ships GA at $10/$50 per million tokens with a 1M context - and safety classifiers that return refusals as HTTP 200 responses, so every integration needs refusal handling, a fallback path, and new billing rules.
Opus 5 ships at the same $5/$25 as Opus 4.8 with near-Fable agentic quality - more than double Opus 4.8 on Frontier-Bench, within 0.5% of Fable on CursorBench at half the cost per task - so escalate to Fable only when the peak or the refusal surface is worth it.