Skip to main content
AI Choice Engine

Model comparison

Claude Fable 5 vs Claude Sonnet 5

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

Claude Fable 5: profile checked October 25, 2026Claude Sonnet 5: profile checked October 25, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

Anthropic

Claude Fable 5

Frontier

vs

Anthropic

Claude Sonnet 5

Balanced

AI model capability comparison
SpecificationClaude Fable 5Claude Sonnet 5
ProviderAnthropicAnthropic
TierFrontierBalanced
Context window1M1M
Max output128K128K
Input / 1M tokens$10Winner: $2
Output / 1M tokens$50Winner: $10
WeightsClosedClosed
ParametersNot verifiedUnverifiedNot verifiedUnverified
Reasoning levelslow, medium, high, xhigh, maxlow, medium, high, xhigh, max
Modalitiestext, imagetext, image
API model idclaude-fable-5claude-sonnet-5
ReleasedJune 9, 2026June 30, 2026
Terminal-Bench 2.1 · source date Claude Sonnet 5: 2026-06-30Not verifiedUnverified80.4
Humanity's Last Exam · source date Claude Sonnet 5: 2026-06-30Not verifiedUnverified57.4
LiveBench · source date Claude Sonnet 5: 2026-09-05Not verifiedUnverified76

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Pricing tiers

Claude Fable 5: Standard USD/MTok input/output $10/$50 with no long-context surcharge; cache reads $1, 5-minute writes $12.50, 1-hour writes $20. Batch $5/$25. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Adaptive thinking is always on; default effort high. Knowledge cutoff January 2026; retirement not sooner than June 9, 2027. Historical access suspension June 12 and restoration July 1, 2026 remain separate events. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens.

Claude Sonnet 5: Standard USD/MTok input/output $2/$10 with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50, 1-hour writes $4. Batch $1/$5. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff January 2026; retirement not sooner than June 30, 2027. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens.

FrontierRecord checked October 25, 2026

Claude Fable 5

Claude Fable 5 is Anthropic's June 2026 long-running-agent model, now 'Active (legacy)' behind Fable 5.1 at the same $10/$50 price.

Best for

  • Long-running agents
  • Frontier reasoning
  • Enterprise work

Watch out

Superseded: Fable 5.1 has the same base input/output prices and lower cache-read pricing ($0.25 vs $1 per million tokens). Savings depend on eligible cached requests; evaluate the successor against your pinned workloads.

BalancedRecord checked October 25, 2026

Claude Sonnet 5

Claude Sonnet 5 is Anthropic's previous Sonnet generation for high-volume agentic work at $2/$10.

Best for

  • Everyday generation
  • High-volume agents
  • Cost-sensitive work

Watch out

Active legacy, still served. Sonnet 5.5 is recommended at the same base input/output price with a lower $0.10 cache-read price and breaking thinking/tool/streaming changes. Setting temperature, top_p or top_k returns an error; check the exact endpoint before migrating. Earlier benchmark results remain this model's observations.

When the cheaper one wins

Claude Sonnet 5 is cheaper on output at $10 per million tokens against $50 for Claude Fable 5 — about 5.0×. 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. On DeepSWE 1.1, Claude Sonnet 5 is 53.8% Pass@1 at $26.4/task versus Claude Fable 5 at 69.9% / $13.41/task. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

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.
  • 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
  • No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
  • Verified within the last 90 days — Older of the two catalog checks was 1 day 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.

Related comparisons

Diving deeper on one model? Claude Fable 5 · Claude Sonnet 5

Common questions

Claude Fable 5 vs Claude Sonnet 5

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

Is Claude Fable 5 or Claude Sonnet 5 cheaper for input?
Claude Sonnet 5 is cheaper at $2 per million input tokens, against $10 for Claude Fable 5 — roughly 5.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Fable 5: Standard USD/MTok input/output $10/$50 with no long-context surcharge; cache reads $1, 5-minute writes $12.50, 1-hour writes $20. Batch $5/$25. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Adaptive thinking is always on; default effort high. Knowledge cutoff January 2026; retirement not sooner than June 9, 2027. Historical access suspension June 12 and restoration July 1, 2026 remain separate events. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens. Claude Sonnet 5: Standard USD/MTok input/output $2/$10 with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50, 1-hour writes $4. Batch $1/$5. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff January 2026; retirement not sooner than June 30, 2027. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens.
Is Claude Fable 5 or Claude Sonnet 5 cheaper for output?
Claude Sonnet 5 is cheaper at $10 per million output tokens, against $50 for Claude Fable 5 — roughly 5.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Fable 5: Standard USD/MTok input/output $10/$50 with no long-context surcharge; cache reads $1, 5-minute writes $12.50, 1-hour writes $20. Batch $5/$25. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Adaptive thinking is always on; default effort high. Knowledge cutoff January 2026; retirement not sooner than June 9, 2027. Historical access suspension June 12 and restoration July 1, 2026 remain separate events. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens. Claude Sonnet 5: Standard USD/MTok input/output $2/$10 with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50, 1-hour writes $4. Batch $1/$5. US-only inference adds 10% to input/output and cache reads/writes on Anthropic-operated routes where supported; Foundry uses US Data Zone Standard. Bedrock and Google-managed Google Cloud have independent regional prices. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff January 2026; retirement not sooner than June 30, 2027. Server-side tools can add usage fees; tool schemas/results and thinking consume billable tokens.
Which has the larger context window, Claude Fable 5 or Claude Sonnet 5?
Both accept about 1M tokens of context, so document length will not decide between them.
Do Claude Fable 5 and Claude Sonnet 5 support the same reasoning levels?
Both expose these named effort settings: "low", "medium", "high", "xhigh", "max". The same labels do not guarantee equal compute budgets or behavior across providers. Compare quality, latency and cost on your own tasks.
Should I use Claude Fable 5 or Claude Sonnet 5?
We classify Claude Fable 5 in the frontier tier and Claude Sonnet 5 in the balanced tier. Test whether either meets your accuracy, tool-use and latency requirements before choosing on price.

Next step

Choosing between them

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

  • Input price: Claude Sonnet 5 costs $2 per 1M tokens versus $10 for Claude Fable 5 — a 5x difference at the headline tier.
  • Positioning: Claude Fable 5 sits in the frontier tier, Claude Sonnet 5 in the balanced tier. Compare accuracy, reliability, latency, and cost on representative tasks before choosing.
Run the model pickerEstimate stack costAll model comparisons

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