Claude Fable 5: AI Large Language Models

Claude Fable 5 is the latest flagship model from Anthropic. Supports text and image inputs with advanced reasoning and creative capabilities. Token-based pricing: $8.00/M input tokens, $40.00/M output tokens. Two endpoints: standard async (/claude-fable-5) and live streaming (/claude-fable-5/stream) via SSE.

📝

Overview

About this model

Claude Fable 5 is the latest flagship model from Anthropic, delivering top-tier reasoning, creative writing, and multimodal analysis. With support for both text and image inputs, it excels at complex multi-step tasks, technical work, and long-form content generation. Pricing is token-based: $8.00 per million input tokens and $40.00 per million output tokens. A newer, more capable version, Claude Fable 5.1, adds a 1M-token context window and always-on adaptive extended thinking for long-horizon agentic and research tasks.

1Complex Reasoning: Tackle multi-step logic, deep analysis, and research synthesis with state-of-the-art accuracy.
2Creative Writing: Generate long-form stories, scripts, essays, and creative content with nuanced style control.
3Coding & Engineering: Write, review, debug, and refactor code across any language with expert-level understanding.
4Multimodal Analysis: Combine image and text inputs to extract insights from diagrams, screenshots, and documents.
💰

Pricing & Value

Cost analysis

muapiapp$8.00/M input tokens, $40.00/M output tokens

Token-based billing. Minimum $0.001 per call.

Anthropic (official)~$15.00/M input tokens, ~$75.00/M output tokens

Official pricing via api.anthropic.com. Muapiapp pricing is significantly lower.

Fal.aiNot available

Claude Fable 5 is not available on Fal.ai.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

The user message or instruction.

Default ValueExplain quantum entanglement in simple terms.
Image URLstring

Optional image URL for multimodal requests.

Default Valueundefined
System Promptstring

Optional system-level instruction to guide model behavior.

Default ValueYou are a concise and precise assistant.
📖

Implementation Guide

Developer documentation

Standard (Async)

POST /api/v1/claude-fable-5 — returns request_id, poll for result via /api/v1/predictions/{id}/result.

Streaming (SSE)

POST /api/v1/claude-fable-5/stream — returns a live Server-Sent Events stream (Content-Type: text/event-stream). Each chunk has the format data: {"choices":[{"delta":{"content":"text"}}]}, ending with data: [DONE].

See Streaming Documentation for full code examples.

Common Questions

Frequently asked

How is pricing calculated?

Pricing is token-based: $8.00 per million input tokens and $40.00 per million output tokens. The minimum charge per call is $0.001. Actual cost is deducted after each call based on token counts returned by the model.

What is the difference between /claude-fable-5 and /claude-fable-5/stream?

/claude-fable-5 is async — you receive a request_id and poll for the result. /claude-fable-5/stream returns a live SSE stream. Use streaming for chat UIs; use the async endpoint for workflows and automation.

Does Claude Fable 5 support images?

Yes. Pass an image_url in the request body to include an image as part of the user message for multimodal analysis.

Is there a newer version than Claude Fable 5?

Yes. [Claude Fable 5.1](/playground/claude-fable-5-1) is Anthropic's newer flagship release, adding a 1M-token context window and always-on adaptive extended thinking for long-horizon agentic coding and research tasks.