Anthropic model product
Claude Fable 5
Claude Fable 5 is Anthropic's generally available deployment of the same underlying weights as the restricted Claude Mythos 5 model.
Updated Aug 17, 2026. Default version: Claude Fable 5
LLMBoard Score95.2Claude Fable 5
Coverage40%17 benchmark families
Context window1MTokens
Official input price$10Anthropic API
Claude Fable 5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Fable 5 Benchmark Results
Benchmark scores for Claude Fable 5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBlueprint-Bench 2 | Score38.6% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkExploitBench | Score78.0% | Rank01 | Participants5 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score53.5% | Rank01 | Participants16 | Percentile100.0% | EvidenceB | Evaluated |
| BenchmarkFrontierSWE | Score90.0% | Rank01 | Participants16 | Percentile100.0% | EvidenceB | Evaluated |
| BenchmarkHealthBench Professional | Score66.0% | Rank01 | Participants9 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score13.3% | Rank01 | Participants13 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score80.0% | Rank01 | Participants50 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score95.0% | Rank01 | Participants111 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkBioMysteryBench | Score46.1% | Rank02 | Participants3 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score70.0% | Rank02 | Participants25 | Percentile95.8% | EvidenceB | Evaluated |
| BenchmarkOSWorld-Verified | Score85.0% | Rank02 | Participants24 | Percentile95.7% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score56.3% | Rank03 | Participants26 | Percentile92.0% | EvidenceB | Evaluated |
| BenchmarkFrontierCode | Score46.3% | Rank03 | Participants4 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score64.5% | Rank03 | Participants99 | Percentile98.0% | EvidenceC | Evaluated |
| BenchmarkGDP.pdf | Score29.8% | Rank04 | Participants6 | Percentile40.0% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score78.3% | Rank05 | Participants38 | Percentile89.2% | EvidenceB | Evaluated |
| BenchmarkAutomationBench | Score17.4% | Rank09 | Participants12 | Percentile27.3% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score84.3% | Rank09 | Participants28 | Percentile70.4% | EvidenceC | Evaluated |
Claude Fable 5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent praise complaint | Categoryoverall | Rank01 | Rating / score0.3 | VotesN/A | Observations5.1K | Result date |
| Arenadocument style control | Categoryoverall | Rank01 | Rating / score1506.7 | Votes5,792 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank01 | Rating / score1236.8 | Votes20,630 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank01 | Rating / score1506.6 | Votes21,439 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank01 | Rating / score1330.5 | Votes8,333 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank01 | Rating / score1314.7 | Votes8,333 | ObservationsN/A | Result date |
| Arenaagent | Categoryoverall | Rank02 | Rating / score0.1 | VotesN/A | Observations911.7K | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank03 | Rating / score0.1 | VotesN/A | Observations18.5K | Result date |
| Arenasearch | Categoryoverall | Rank03 | Rating / score1236.8 | Votes20,630 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank04 | Rating / score1504.2 | Votes5,792 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank04 | Rating / score1216.5 | Votes20,630 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank05 | Rating / score0.1 | VotesN/A | Observations17.2K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank05 | Rating / score0.1 | VotesN/A | Observations17.1K | Result date |
| Arenatext | Categoryoverall | Rank05 | Rating / score1493.3 | Votes21,439 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank05 | Rating / score1485.5 | Votes21,422 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank06 | Rating / score1626.9 | Votes7,867 | ObservationsN/A | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank12 | Rating / score0.0 | VotesN/A | Observations853.8K | Result date |
Claude Fable 5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $10 input, $50 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $3 input, $18.5 output per 1M via Xpersona
- Tracked offerings
- 31
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDclaude-fable-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXpersona | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$3 | Output / 1M$18.5 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderFreeModel | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderNeon | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOpenCode Zen | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-fable-latest | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderModelis | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAbacus | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$11 | Output / 1M$55 | Context1M | Updated |
| ProviderPioneer | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$11 | Output / 1M$55 | Context1M | Updated |
| ProviderVenice AI | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$12 | Output / 1M$60 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Fable 5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Fable 5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed9.081 tok/s | Catalog Latency28.237 s | Max Input1M | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Fable 5 Specifications
Technical details for the model's default version.
- Version
- Claude Fable 5
- Released
- Jun 9, 2026
- Knowledge cutoff
- Jan 31, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 128K
- Inputs
- image, pdf, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Fable 5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Fable 5 | Released | LLMBoard95.2 | ParametersN/A | Context1M | Max output128K | Open weightsNo | LicenseProprietary |
Claude Fable 5 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Claude Fable 5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 5
Anthropic
AN
Claude Mythos
Anthropic
AN
Claude Opus 4.8
Anthropic
AN
Claude Opus 4.7
Anthropic
AN
Claude Sonnet 5
Anthropic
AN
Claude Opus 4.6
Anthropic
What is Claude Fable 5?
Key information about Claude Fable 5 and its available data.
Claude Fable 5 is Anthropic's generally available deployment of the same underlying weights as the restricted Claude Mythos 5 model. Anthropic positions the model as a new capability tier above Opus: Mythos 5 is the unsafeguarded trusted-access configuration, while Fable 5 adds production safeguards for public use.
8 in safeguarded domains. 4%. Fable 5 uses classifiers for cybersecurity, biology and chemistry, and distillation attempts; in Claude client apps these requests fall back to the latest Claude Opus model, while the Messages API blocks by default unless developers implement or opt into fallback. 03% of traffic.
The model was trained on a proprietary mix of public web data, public and private datasets, and synthetic data. Anthropic prices Fable 5 at $10 per million input tokens and $50 per million output tokens, and exposes it through the Claude API as `claude-fable-5`.
Data as of 2026-08-17.
FAQ
Common questions about Claude Fable 5.
When was Claude Fable 5 released?
Claude Fable 5's default version was released on Jun 9, 2026.
How much does Claude Fable 5 cost?
Claude Fable 5's official API price is $10 per million input tokens and $50 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $3 input and $18.5 output via Xpersona.
Who created Claude Fable 5?
Claude Fable 5 was created by Anthropic.
What is the context window for Claude Fable 5?
The default version has a 1M token context window.
Is Claude Fable 5 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Fable 5?
31 provider offerings are linked to the default version.
What models should I compare Claude Fable 5 with?
Nearby ranked alternatives include Claude Opus 5, GPT-5.6-Sol, Claude Mythos.