Claude Fable 5.1 vs Claude Haiku 4.5
Side by side on the numbers both labs publish: what they cost, how much they hold, when they shipped. No benchmarks, because we haven't run any.
From Anthropic's and Anthropic's own docs · updated 2026-09-05 10:32 UTC
- Claude Fable 5.1 charges 10x what Claude Haiku 4.5 does for the words it writes back.
- Claude Fable 5.1 holds 1M tokens at once against 200K, so long documents go further before you have to cut them up.
- At steady daily use, Claude Haiku 4.5 works out around $2.56 a month and Claude Fable 5.1 around $26.
- Claude Fable 5.1 is the newer of the two, out on 2026-09-01 against 2025-10-15.
| Claude Fable 5.1 | Claude Haiku 4.5 | |
|---|---|---|
| Lab | Anthropic | Anthropic |
| Released | 2026-09-01 | 2025-10-15 |
| Status | released | released |
| Built in | US | US |
| Context window | 1M | 200K |
| Longest reply | 128K | 64K |
| Input, per million | $10.00 | $1.00 |
| Output, per million | $50.00 | $5.00 |
| API name | claude-fable-5-1 | claude-haiku-4-5-20251001 |
| A few questions a day, a month | $4.80 | $0.48 |
| Steady daily use, a month | $26 | $2.56 |
| Something running all day, a month | $600 | $60 |
The dot marks the cheaper price, the bigger window or the longer reply. Monthly costs assume the workload in the row, thirty days, list prices, no caching or batch discounts. Price every model at once.
What this comparison can't tell you
Which one writes better. Which one is easier to steer. Which one your own prompts already work on. Those depend on your work, and a spec table has never answered them.
What it does settle is the money and the ceiling. If two models both clear your bar, the table tells you which one is cheaper to live with, and by how much.
Where the numbers came from
Claude Fable 5.1: Anthropic documentation. Claude Haiku 4.5: Anthropic documentation. We refetch both with the rest of the pipeline, so the stamp at the top says when we last looked.
Compare two others · everything on Claude Fable 5.1 · everything on Claude Haiku 4.5