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 2026-08-26).
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 2026-08-26 against official rate cards — the tracker keeps the change log. Note: Claude Sonnet 5 — promotional pricing through Aug 31, 2026.
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. Sonnet's promo rate (through Aug 31, 2026) makes the bump unusually cheap right now.
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.