TL;DR — Sonnet 5 is exactly 2× Haiku 4.5 ($2/$10 vs $1/$5) — the cleanest price ratio in Anthropic's ladder. Every number below is from our weekly-verified pricing tracker (verified 2026-09-13).
Pricing side by side (per 1M tokens, USD)
| Model | Provider | Input | Output |
|---|---|---|---|
| Claude Sonnet 5 | Anthropic | $2 | $10 |
| Claude Haiku 4.5 | Anthropic | $1 | $5 |
Verified 2026-09-13 against official rate cards — the tracker keeps the change log. Note: Claude Sonnet 5 — introductory $2/$10 made permanent; the planned Sept 1, 2026 rise to $3/$15 was cancelled.
What a real month costs
At a standard workload of 10M input + 2M output tokens/month:
- Claude Sonnet 5: $40.00
- Claude Haiku 4.5: $20.00
On this mix, Claude Haiku 4.5 is the cheaper column (2.0× gap). Your ratio will differ — run your own mix through the LLM cost calculator.
Choose Claude Sonnet 5 if
the task involves actual reasoning: synthesis, structured writing, multi-constraint answers. At a permanent $2/$10, the step up from Haiku is cheap enough to take by default.
Choose Claude Haiku 4.5 if
the work is classification, extraction, short chat turns, or anything latency-sensitive — Haiku 4.5 at $1/$5 is built to absorb exactly this bulk traffic.
Routing decision card
- Haiku takes the bulk lane, Sonnet takes the quality-middle lane, and the pair covers most non-frontier traffic
- The 2× ratio makes budget math trivial: shifting 30% of Haiku traffic up to Sonnet raises that slice's cost by exactly 2×
- Both benefit from cache + batch stacking on stable prompts
- The router answer: most teams shouldn't hard-pick one — ClawRouters routes each request to whichever side fits it, so the comparison becomes a per-call decision instead of a bet.
Per-model detail: Claude Haiku 4.5 deep dive
Part of the LLM model comparison index. Prices move fast in 2026 — the tracker logs every change with dates.