Claude Fable 5.2 vs Claude Haiku 5.5
API pricing, context, and independently measured performance, side by side. Claude Haiku 5.5 starts 99% cheaper on input than Claude Fable 5.2 at list prices.
Claude Fable 5.2
Anthropic · released Nov 9, 2026
Best input$8.00 / MTok
Best output$40.00 / MTok
Context1M
Providers5
Fastest measured—
VisionToolsReasoningStructured outputPrompt caching
Claude Haiku 5.5
Anthropic · released Oct 7, 2026
Best input$0.10 / MTok
Best output$0.50 / MTok
Context1M
Providers10
Fastest measured2.8s°ᴿ TTFT · 615 tok/s
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Claude Fable 5.2 |  Google | $8.00 | $40.00 | — | — | — |
| Claude Fable 5.2 |  Amazon Bedrock | $8.00 | $40.00 | — | — | — |
| Claude Fable 5.2 |  Azure | $8.00 | $40.00 | — | — | — |
| Claude Haiku 5.5 | Google | $0.10 | $0.50 | 3.3s°ᴿ | 807°ᴿ tok/s | — |
| Claude Haiku 5.5 |  Claude Platform on AWS | $0.10 | $0.50 | 3.4s°ᴿ | 718°ᴿ tok/s | — |
| Claude Haiku 5.5 | Azure | $0.10 | $0.50 | 2.8s°ᴿ | 615°ᴿ tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page