What is Anthropic: Claude Fable 5's context window?

Anthropic: Claude Fable 5 supports a context window of 1,000,000 tokens, allowing you to process large documents and maintain long conversations.

How to use Anthropic: Claude Fable 5 API via Ofox?

Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

Anthropic: Claude Fable 5

Name: Anthropic: Claude Fable 5
Brand: anthropic
Price: 10 USD
Availability: InStock
Rating: 5 (1 reviews)

Chat

anthropic/claude-fable-5

Compare Try in Playground Get Started

Anthropic Claude Fable 5 - Mythos-class, long-horizon agentic autonomy

Context Window

Max Output Tokens

128K

Released

2026-06-09

Capabilities

VisionFunction CallingReasoningPrompt CachingPDF Input

Available Providers

AzureAnthropic

Supported Protocols

anthropic

Providers

Anthropic

Input Tokens

$10/M

Output Tokens

$50/M

Cache Read

$1/M

Cache Write (5 min)

$12.5/M

Cache Write (1 hour)

$20/M

Web Search

$0.015/R

Protocols

anthropic

Azure

Input Tokens

$10/M

Output Tokens

$50/M

Cache Read

$1/M

Cache Write (5 min)

$12.5/M

Cache Write (1 hour)

$20/M

Web Search

$0.015/R

Protocols

anthropic

Playground

Open in OfoxChat

Chat with this model right here.

Conversations live only in this page and are never stored.

Conversations are not saved — leaving or refreshing this page clears them.

Code Examples

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.ofox.ai/anthropic",
    api_key="YOUR_OFOX_API_KEY",
)

message = client.messages.create(
    model="anthropic/claude-fable-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(message.content[0].text)

Uptime & Status

Benchmarks

LMArena ↗Evaluated as claude-fable-5

Anthropic: Claude Fable 5 scores 1507 in the Overall category of the LMArena text leaderboard (style control), ranking #1 of 374 models based on 7,856 human preference votes (updated 2026-07-12).

Benchmark scores for claude-fable-5 on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1507	1500–1515	#1 of 374	7,856
Hard Prompts	1534	1526–1543	#1 of 374	5,239
Coding	1548	1535–1561	#4 of 369	2,184
Math	1551	1522–1580	#1 of 362	398
Creative Writing	1509	1493–1525	#1 of 372	1,446
Instruction Following	1514	1502–1526	#1 of 374	2,752
Chinese	1549	1519–1578	#2 of 344	439

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.