Claude Fable 5 benchmarks, pricing and specs
Claude Fable 5 is an Anthropic model released on June 9, 2026 that takes text and image input and produces text. It costs $10 per 1M input tokens and $50 per 1M output tokens and accepts up to 1,000,000 tokens of context. It scores 1504 Elo on Arena Text, #2 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $10
- Per 1M output tokens
- $50
- Context window
- 1M
- Arena Text
- 1504 Elo · #2/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- Anthropic
- Model family
- Claude Fable
- Release date
- June 9, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- text, image
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning
Claude Fable 5 pricing
It is tied for the most expensive of 37 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Anthropic's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1504 Elo | #2 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 85.9% | #30 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 87% | #8 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 70.7% | #6 of 34 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Claude Fable 5 is Anthropic's highest-capability widely released model for demanding reasoning and long-horizon agentic work
Cautions
- Fable requires 30-day data retention, and classifier-triggered requests fall back to Claude Opus 4.8
Best for
- Long-horizon coding, reasoning, and knowledge-work evaluations
Alternatives to Claude Fable 5
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
Claude Opus 5.5
- 60% cheaper per 1M input tokens, $4 vs $10
- 3 points higher on Arena Text, 1507 vs 1504
GPT-6 Astra
- Same price per 1M input tokens, $10
- 29 points lower on Arena Text, 1475 vs 1504
- From OpenAI
Claude Mythos 5.1
- Same price per 1M input tokens, $10
GPT-5.5
- 50% cheaper per 1M input tokens, $5 vs $10
- 22 points lower on Arena Text, 1482 vs 1504
- From OpenAI
Compare Claude Fable 5 with
Articles about Claude Fable 5
- Claude Fable 5 vs GPT 5.6: Benchmarks, Cost, Access, and Best Use CasesJuly 3, 2026
- Claude Fable 5 Is Back After 3 Weeks Ban: A Production Team GuideJuly 2, 2026
- Did the US government ban Claude Fable 5?June 20, 2026
- Claude Fable 5 vs GPT 5.5 vs Gemini 3.5 Flash ThinkingJune 11, 2026
- Claude Fable 5: A Practical Guide for Production AI WorkflowsJune 11, 2026
Other Claude Fable models
Claude Fable 5 FAQ
How much does Claude Fable 5 cost?
Claude Fable 5 costs $10 per 1M input tokens and $50 per 1M output tokens at the standard tier. It is tied for the most expensive of 37 current text models priced per 1M input tokens. Source: Anthropic, verified October 11, 2026.
What is the context window of Claude Fable 5?
Claude Fable 5 accepts up to 1,000,000 tokens of context. It can return up to 128,000 tokens in one response. That ranks #24 of 44 current text models by context length.
How does Claude Fable 5 score on independent benchmarks?
Claude Fable 5 scores 1504 Elo on Arena Text, #2 of 39 current models (Arena, measured October 8, 2026), 85.9% on GPQA Diamond, #30 of 37 current models (Epoch AI, measured October 12, 2026) and 87% on FrontierMath Tiers 1-3 (v2), #8 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not Anthropic's own launch figures.
Is Claude Fable 5 open source or API only?
Claude Fable 5 is available through Anthropic's API only; its weights are not published.
What are the best alternatives to Claude Fable 5?
The closest current alternatives by price and measured performance are Claude Opus 5.5 (60% cheaper per 1M input tokens, $4 vs $10), GPT-6 Astra (same price per 1M input tokens, $10), Claude Mythos 5.1 (same price per 1M input tokens, $10) and GPT-5.5 (50% cheaper per 1M input tokens, $5 vs $10).
Sources
- Claude Fable 5 and Claude Mythos 5 · Anthropic · official · verified August 7, 2026
- Claude models overview · Anthropic · official · verified August 7, 2026
- Claude API pricing · Anthropic · official · verified October 11, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Claude Fable 5 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/claude-fable-5
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Claude Fable 5 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls