# Anthropic: claude-fable-5

- Model ID: `claude-fable-5`
- Provider: Anthropic
- Web version: https://www.moleapi.com/en/models/anthropic/claude-fable-5
- Content status: catalog

## Model introduction

Claude model by Anthropic for general chat, writing, coding assistance, and tool-assisted workflows.

## Model capabilities

- OpenAI compatible
- Anthropic compatible
- Prompt cache

### Verified specifications

- Catalog status: Currently available on MoleAPI
- Compatible protocols: anthropic, openai
- Available billing groups: Standard, Discount, Relay

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

- Input: $10 / 1M tokens
- Output: $50 / 1M tokens
- Cache read: $1 / 1M tokens
- Cache write: $12.5 / 1M tokens

### Discount (discount, x0.8)

- Input: $8 / 1M tokens
- Output: $40 / 1M tokens
- Cache read: $0.8 / 1M tokens
- Cache write: $10 / 1M tokens

### Relay (relay, x0.3)

- Input: $3 / 1M tokens
- Output: $15 / 1M tokens
- Cache read: $0.3 / 1M tokens
- Cache write: $3.75 / 1M tokens

### Access protocols

| Protocol | Method | Endpoint |
| --- | --- | --- |
| anthropic | POST | /v1/messages |
| openai | POST | /v1/chat/completions |

- Live pricing source: https://home.moleapi.com/api/pricing

## About claude-fable-5

# Claude Fable 5 model guide

Claude Fable 5 is Anthropic’s most capable generally available model, positioned for difficult, long-running coding and knowledge-work tasks. Anthropic highlights autonomous agents, large software migrations, multi-stage research and analysis, and visual document reasoning as core workloads. [6]

## Positioning and core capabilities

Claude Fable 5 is a Mythos-class model intended for ambitious professional work that can span multiple stages and extended execution periods. Anthropic describes it as able to plan work across stages, delegate to sub-agents, validate its own output, and operate in asynchronous agent workflows. [3][6]

Its stated capabilities cover software engineering, complex implementations, enterprise research and analysis, and reasoning over visual and document-based inputs. [6]

## Capabilities and specifications

Claude Fable 5 was announced on June 9, 2026, and Anthropic restored access on July 1, 2026, following a temporary suspension announced on June 12, 2026. [3][6]

| Specification | Detail |
|---|---|
| Model class | Mythos-class model. [3] |
| General availability | Anthropic describes Fable 5 as generally available. [3][6] |
| Supported work | Long-running coding, autonomous agents, knowledge work, research, and visual-document analysis. [6] |
| Visual reasoning inputs | Diagrams, charts, tables, files, PDFs, and design materials. [6] |
| Deployment channels | Claude applications, the Claude Platform, marketplaces, AWS, Google Cloud, and Microsoft Foundry. [6] |

## Use cases

Claude Fable 5 is positioned for projects that require sustained reasoning, iterative implementation, and validation across complex tasks. [6]

- **Large software migrations:** Anthropic highlights large migrations and complex implementations as coding workloads for Fable 5. [6]
- **Autonomous coding agents:** The model is designed for agent harnesses that plan, delegate work, and check results across extended workflows. [6]
- **Multi-stage enterprise analysis:** Anthropic positions Fable 5 for research, analysis, and professional knowledge work involving multiple dependent stages. [6]
- **Document and visual analysis:** The model can analyze diagrams, charts, tables, files, PDFs, and design-validation materials. [6]
- **Scientific and technical research:** Anthropic includes scientific research among the model’s intended knowledge-work applications. [6]

## Material limitations

Claude Fable 5 applies enhanced safeguards to cybersecurity and biology requests, and flagged requests can be routed automatically to less capable Opus models. [6]

In most Claude applications, Anthropic states that cybersecurity requests may route to Opus 4.8 and biology requests may route to Opus 5. [6] Harmless requests can also be captured by these safeguards. [6]

Use of Claude Fable 5 requires 30-day data retention for safety monitoring. [6]

## Sources

- [3] [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5)
- [6] [Claude Fable](https://www.anthropic.com/claude/fable)


## Code examples

### cURL

```bash
curl https://api.moleapi.com/v1/chat/completions \
  -H "Authorization: Bearer $MOLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-fable-5","messages":[{"role":"user","content":"Hello"}]}'
```

## More related models

- [claude-opus-5](https://www.moleapi.com/en/models/anthropic/claude-opus-5) — Anthropic
- [claude-sonnet-5](https://www.moleapi.com/en/models/anthropic/claude-sonnet-5) — Anthropic
- [claude-opus-4.6](https://www.moleapi.com/en/models/anthropic/claude-opus-4.6) — Anthropic
- [gpt-5.6-luna](https://www.moleapi.com/en/models/openai/gpt-5.6-luna) — OpenAI
- [gpt-5.6-sol](https://www.moleapi.com/en/models/openai/gpt-5.6-sol) — OpenAI
- [gpt-5.6-terra](https://www.moleapi.com/en/models/openai/gpt-5.6-terra) — OpenAI

## Frequently asked questions

### How is claude-fable-5 priced?

Prices are read from the MoleAPI console API and update with model prices, context tiers, and account groups.

### How can I access claude-fable-5?

The catalog currently lists anthropic, openai.

### How do I switch an existing project to claude-fable-5?

Keep the MoleAPI API address and key, replace the model parameter, and check protocol-specific parameters.

### Where do the claude-fable-5 details come from?

Only confirmed availability, pricing, and protocol details from the MoleAPI catalog are included.