Claude Haiku 4.5 → Claude Sonnet 5 Routing
Routing easy queries to Claude Haiku 4.5 and hard ones to Claude Sonnet 5? This computes the blended savings — and the re-run rate at which the double-charges make it stop paying.
For teams routing easy queries to a cheap model and hard ones to an expensive one — computes the blended savings AND the break-even re-run rate, since misrouted queries pay twice, not a 'routing always saves' assumption.
Model prices from OpenRouter · updated 2026-07-13
01 Your cascade
$0.004000/request
$0.008000/request
02 Routing vs all-expensive
Routing saves $2,240/month (28%) — you're under the 50% re-run break-even.
Break-even re-run rate: 50% · you're at 10%
Claude Sonnet 5 costs 2× Claude Haiku 4.5 per request — so you can misroute up to 50% before routing stops paying.
Related cost calculators
Prices from OpenRouter, snapshot 2026-07-13, synced daily. Blended = requests × [(1−easy)×expensive + easy×(1−rerun)×cheap + easy×rerun×(cheap+expensive)]. Break-even re-run rate = 1 − cheap/expensive per-request cost. Prompt caching and model quality aren't modeled — dollar cost only. All math runs in your browser.
How the math works
Routing sends the easy 70% of queries to Claude Haiku 4.5 ($0.004000/request) and keeps the hard 30% on Claude Sonnet 5 ($0.008000/request). Running everything on Claude Sonnet 5 would cost $8,000/month; routing brings it to $5,760. That saves $2,240/month (28%).
The number nobody prices is the re-run penalty. When Claude Haiku 4.5 gets a query it can't handle, you re-run it on Claude Sonnet 5 — so that query pays twice (the wasted cheap attempt plus the expensive redo). At a 10% re-run rate that double-charge is $840/month of pure waste, quietly eating into the routing savings.
Same baseline, one break-even: routing wins as long as your re-run rate stays under 50% (that's 1 − cheap/expensive cost). Because Claude Sonnet 5 costs 2× what Claude Haiku 4.5 does, you can misroute a lot before it stops paying — you're at 10%, with 40 points of headroom.
The lever isn't "route more" — it's routing accuracy. Pushing more traffic to the cheap model only helps if the cheap model actually handles it; every misroute costs a full expensive call on top of the wasted cheap one. A cheaper fallback model, or a better router that mis-sends fewer queries, moves the number more than a bigger cheap share.
Not modeled: prompt caching (applies to both models and roughly cancels out of the comparison), and any quality difference between the models — this page compares dollar cost only. Inference prices sync daily from OpenRouter (updated 2026-07-13); this is an accounting comparison of two catalog models, not a separate price source. All math runs client-side with tested code.
Frequently asked questions
Does routing to Claude Haiku 4.5 actually save money for a Claude Haiku 4.5 → Claude Sonnet 5 cascade?
At this page's defaults — 70% easy share, 10% re-run rate — yes: $2,240/month (28%) vs running everything on Claude Sonnet 5. It holds as long as your re-run rate stays under 50%.
What's the break-even re-run rate?
50% — computed as 1 − (cheap cost ÷ expensive cost). Below it, routing saves; above it, the re-run double-charges outweigh the savings. Because Claude Sonnet 5 is so much pricier per request here, the break-even is high — you have real headroom for an imperfect router.
Why do misrouted queries cost double?
Because a query sent to Claude Haiku 4.5 that fails still billed for the cheap attempt — then you re-run it on Claude Sonnet 5 and pay for that too. So each misroute is cheap + expensive, not just expensive. At 10% that's $840/month here.
Should I just route more traffic to the cheap model?
Only if the cheap model handles it. Raising the cheap share helps when re-run stays low, but if pushing more queries down means more of them bounce back, each bounce costs a full expensive call plus the wasted cheap one. Router accuracy beats router aggressiveness.
Are these prices current?
Both models' prices sync daily from OpenRouter (updated 2026-07-13). This mold adds no separate price source — it's an accounting comparison of two live catalog models, so it stays accurate as prices change automatically.
How much can a Claude Haiku 4.5 → Claude Sonnet 5 cascade save at best?
The ceiling is routing 100% to Claude Haiku 4.5 with zero re-runs: $4,000/month vs all-Claude Sonnet 5. Real savings land below that, scaled by your easy share and re-run rate — tune both sliders to see yours.