# Claude Fable 5.1

Claude Fable 5.1 is a text generation model from Anthropic, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $10.00 per million input tokens. The advertised output rate is $50.00 per million output tokens.

- Model identifier: ` anthropic/claude-fable-5-1 `
- Creator: Anthropic
- Model type: Text generation
- Canonical model page: [Claude Fable 5.1](<https://impossibl.com/anthropic/claude-fable-5-1>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-09-01

## Capabilities and limits

- Context window: 1,000,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` anthropic/claude-fable-5-1 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $10.00 | per million input tokens |
| Output | $50.00 | per million output tokens |
| Cache read | $0.25 | per million cached input tokens |
| Cache write (default retention) | $12.50 | per million tokens |
| Cache write (one-hour retention) | $20.00 | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T10:50:14.034Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-fable-5-1>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 53.37 |
| Omniscience Index | 43.45 |
| GPQA | 93.74% |
| Humanity’s Last Exam | 59.13% |
| SciCode | 63.08% |
| CritPt | 29.71% |
| Terminal-Bench v2.1 | 91.39% |
| Terminal-Bench v4.0 | 52.02% |
| AA-LCR | 85.33% |
| Multilingual LCR | 71.11% |
| Harvey LAB | 93.02% |
| GDPval Elo | 1763.64 |
| GDP.pdf All-pass | 26.20% |
| AutomationBench Partial | 59.38% |
| AnalystAgent | 57.50% |
| Tau Banking | 47.22% |
| coding index (API) | 81.6 |
| agentic index (API) | 58 |
| intelligence index (API) | 53.4 |

### Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-fable-5-1-high>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 51.21 |
| Omniscience Index | 40.80 |
| GPQA | 90.61% |
| Humanity’s Last Exam | 55.93% |
| SciCode | 58.68% |
| CritPt | 30.29% |
| Terminal-Bench v2.1 | 89.89% |
| Terminal-Bench v4.0 | 52.02% |
| AA-LCR | 83.67% |
| Harvey LAB | 92.95% |
| GDPval Elo | 1649.77 |
| GDP.pdf All-pass | 26.80% |
| AutomationBench Partial | 55.32% |
| Tau Banking | 43.09% |
| coding index (API) | 79.1 |
| agentic index (API) | 53.3 |
| intelligence index (API) | 51.2 |

### Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-fable-5-1-low>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 47.04 |
| Omniscience Index | 34.13 |
| GPQA | 88.08% |
| Humanity’s Last Exam | 48.89% |
| SciCode | 56.71% |
| CritPt | 27.71% |
| Terminal-Bench v2.1 | 85.02% |
| Terminal-Bench v4.0 | 40.40% |
| AA-LCR | 82.33% |
| Harvey LAB | 92.33% |
| GDPval Elo | 1503.72 |
| GDP.pdf All-pass | 28.00% |
| AutomationBench Partial | 52.24% |
| Tau Banking | 38.97% |
| coding index (API) | 75.2 |
| agentic index (API) | 47.8 |
| intelligence index (API) | 47 |

### Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-fable-5-1-medium>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 49.06 |
| Omniscience Index | 37.60 |
| GPQA | 88.59% |
| Humanity’s Last Exam | 53.80% |
| SciCode | 56.37% |
| CritPt | 29.14% |
| Terminal-Bench v2.1 | 88.01% |
| Terminal-Bench v4.0 | 44.95% |
| AA-LCR | 84.67% |
| Harvey LAB | 92.65% |
| GDPval Elo | 1579.31 |
| GDP.pdf All-pass | 26.80% |
| AutomationBench Partial | 54.66% |
| Tau Banking | 41.03% |
| coding index (API) | 77.1 |
| agentic index (API) | 50.6 |
| intelligence index (API) | 49.1 |

### Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)

Source: [Evaluation source](<https://artificialanalysis.ai/models/claude-fable-5-1-xhigh>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 53.18 |
| Omniscience Index | 42.38 |
| GPQA | 93.43% |
| Humanity’s Last Exam | 58.71% |
| SciCode | 60.88% |
| CritPt | 31.14% |
| Terminal-Bench v2.1 | 91.01% |
| Terminal-Bench v4.0 | 55.05% |
| AA-LCR | 83.00% |
| Harvey LAB | 93.27% |
| GDPval Elo | 1745.29 |
| GDP.pdf All-pass | 26.20% |
| AutomationBench Partial | 57.77% |
| Tau Banking | 45.77% |
| coding index (API) | 80.7 |
| agentic index (API) | 57.1 |
| intelligence index (API) | 53.2 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/anthropic/claude-fable-5-1/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Claude Fable 5.1?

Claude Fable 5.1 is a text-generation model from Anthropic, available through the Impossibl API.

### How much does Claude Fable 5.1 cost?

Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens through the Impossibl API. Cache reads cost $0.25 per million tokens; cache writes cost $12.50 per million tokens; cache writes with one-hour retention cost $20.00 per million tokens. All rates are in USD.

### What is the context length of Claude Fable 5.1?

Claude Fable 5.1 has a 1,000,000-token context window through the Impossibl API.

### What inputs and outputs does Claude Fable 5.1 support?

Claude Fable 5.1 accepts text and image as input. Claude Fable 5.1 returns text.

### How do I use Claude Fable 5.1 through an API?

Claude Fable 5.1 is available through the Impossibl API. Use anthropic/claude-fable-5-1 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Claude Fable 5.1 released?

Anthropic released Claude Fable 5.1 on September 1, 2026.

Sources: [Creator release announcement](<https://www.anthropic.com/claude/fable>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Claude Fable 5.1: model details and pricing](<https://impossibl.com/anthropic/claude-fable-5-1>)
- [Model directory](<https://impossibl.com/models>)