Model comparison

Claude Fable 5.1 vs Claude Haiku 4.5

Two Anthropic tiers compared on the figures that decide which one a workload actually needs.

Catalog record checked September 5, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Anthropic

Claude Fable 5.1

Frontier

Anthropic

Claude Haiku 4.5

Budget

AI model capability comparison
Specification	Claude Fable 5.1	Claude Haiku 4.5
Provider	Anthropic	Anthropic
Tier	Frontier	Budget
Context window	Winner: 1M	200K
Max output	Winner: 128K	64K
Input / 1M tokens	$10	Winner: $1
Output / 1M tokens	$50	Winner: $5
Weights	Closed	Closed
Parameters	Not disclosedUnverified	Not disclosedUnverified
Reasoning levels	adaptive	Not verifiedUnverified
Modalities	text, image	text, image
API model id	claude-fable-5-1	claude-haiku-4-5-20251001
Released	September 1, 2026	October 15, 2025
Artificial Analysis Intelligence Index (2026-08-14)	Winner: 66	28
Humanity's Last Exam (2026-09-01)	65	Not verifiedUnverified
Terminal-Bench 2.1 (2026-09-05)	91.4	Not verifiedUnverified
DeepSWE 1.1 (2026-09-03)	67.4	Not verifiedUnverified
SWE-bench Verified (2026-02-17)	Not verifiedUnverified	66.6
Terminal-Bench (2025-10-15)	Not verifiedUnverified	40.21

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

2026-09-05: Artificial Analysis Terminal-Bench v2.1 (independent, Terminus 2, max effort — current AA leader)Agentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.
2026-09-03: OpenAI GPT-6 Astra launch chart (independent cross-vendor; Fable 5.1 not on the official Datacurve leaderboard)Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task. Comparability: directly comparable
2026-09-01: Anthropic announcement comparison table (vendor, with tools; 60.9 no tools)Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise. Comparability: comparable with caveat — Subset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
2026-08-14: Artificial Analysis (Non-reasoning)Composite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
2026-02-17: SWE-bench official leaderboard (independent harness: mini-SWE-agent bash-only, $0.33/task; conflicts with vendor 73.3 — both preserved)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
2025-10-15: Anthropic — Introducing Claude Haiku 4.5 (vendor, Terminus 2, no thinking, 6 runs; 41.75 with 32K thinking)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.

Pricing tiers: Claude Fable 5.1: Priced with Fable 5 at $10/$50 per MTok; cache reads cut 75% to $0.25/MTok. Adaptive thinking always on (default effort high); knowledge cutoff Jun 2026. Sibling Mythos 5.1 launched the same day. · Claude Haiku 4.5: Standard $1/$5 per MTok; cache reads 10% of base input. 200K context (vs 1M on Opus/Sonnet 5).

FrontierRecord checked September 3, 2026

Claude Fable 5.1

Claude Fable 5.1 is Anthropic's September 2026 flagship refresh, debuting at the top of LiveBench and the Artificial Analysis Intelligence Index.

Best for

Frontier agents
Hardest reasoning work
Fable 5 workloads at the same price

Watch out

Early-life model: leaderboard position is from launch-week boards; recheck before committing spend.

BudgetRecord checked September 5, 2026

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's fastest, cheapest tier for high-volume classification and extraction.

Best for

High-volume classification
Routine extraction
Latency-sensitive stacks

Watch out

No adaptive thinking; 200K context only. A generation behind Opus/Sonnet 5 — Anthropic lists 2026-10-15 as the earliest possible retirement date.

When the cheaper one wins

Claude Haiku 4.5 is cheaper on output at $5 per million tokens against $50 for Claude Fable 5.1 — about 10×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
3/5 core specs verified on both sides — Not published for at least one side: parameter count, reasoning levels.
1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
Verified within the last 90 days — Newest catalog check was 6 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Claude Fable 5.1: Anthropic pricing — Fable 5.1/Mythos 5.1 $10/$50 (accessed 2026-09-03)
Claude Fable 5.1: Anthropic models overview — Fable 5.1 (1M context, 128K output) (accessed 2026-09-03)
Claude Fable 5.1: Artificial Analysis — Fable 5.1 Intelligence Index 66 #1 (accessed 2026-09-01)
Claude Haiku 4.5: Anthropic — Claude Haiku 4.5 (accessed 2026-08-29)
Claude Haiku 4.5: Anthropic pricing (accessed 2026-08-29)

Related comparisons

Diving deeper on one model? Claude Fable 5.1 · Claude Haiku 4.5

Common questions

Claude Fable 5.1 vs Claude Haiku 4.5

Answered from the verified figures on this page rather than general guidance.

Is Claude Fable 5.1 or Claude Haiku 4.5 cheaper for input?

Claude Haiku 4.5 is cheaper at $1 per million input tokens, against $10 for Claude Fable 5.1 — roughly 10× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Fable 5.1 has tiered pricing: Priced with Fable 5 at $10/$50 per MTok; cache reads cut 75% to $0.25/MTok. Adaptive thinking always on (default effort high); knowledge cutoff Jun 2026. Sibling Mythos 5.1 launched the same day. Claude Haiku 4.5 has tiered pricing: Standard $1/$5 per MTok; cache reads 10% of base input. 200K context (vs 1M on Opus/Sonnet 5).

Is Claude Fable 5.1 or Claude Haiku 4.5 cheaper for output?

Claude Haiku 4.5 is cheaper at $5 per million output tokens, against $50 for Claude Fable 5.1 — roughly 10× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Fable 5.1 has tiered pricing: Priced with Fable 5 at $10/$50 per MTok; cache reads cut 75% to $0.25/MTok. Adaptive thinking always on (default effort high); knowledge cutoff Jun 2026. Sibling Mythos 5.1 launched the same day. Claude Haiku 4.5 has tiered pricing: Standard $1/$5 per MTok; cache reads 10% of base input. 200K context (vs 1M on Opus/Sonnet 5).

Which has the larger context window, Claude Fable 5.1 or Claude Haiku 4.5?

Claude Fable 5.1 accepts 1M tokens against 200K for Claude Haiku 4.5. This only matters if you routinely send very long documents or large codebases.

Should I use Claude Fable 5.1 or Claude Haiku 4.5?

Claude Fable 5.1 is the frontier tier and Claude Haiku 4.5 the budget tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: Claude Haiku 4.5 costs $1 per 1M tokens versus $10 for Claude Fable 5.1 — a 10x difference at the headline tier.
Context: Claude Fable 5.1 takes 1M against 200K for Claude Haiku 4.5 — only decisive if your prompts approach the smaller window.
Positioning: Claude Fable 5.1 sits in the frontier tier, Claude Haiku 4.5 in the budget tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.