LLM Reference
Replicate API

Claude Fable 5 on Replicate API

Claude Fable · Anthropic

Serverless

Last refreshed 2026-07-09. Next refresh: weekly.

Why use Claude Fable 5 on Replicate API?

Replicate API offers Claude Fable 5 with pay-as-you-go pricing at $10.00/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Claude Fable 5 across 8 providers to find the best fit for your use case
Input / 1M
$10.00
Output / 1M
$50.00
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "anthropic/claude-fable-5",
    input={"prompt": "Hello"}
Model ID
anthropic/claude-fable-5

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# anthropic/claude-fable-5 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "anthropic/claude-fable-5",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "anthropic/claude-fable-5", not the LLMReference slug "claude-fable-5".
  • Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare Claude Fable 5 Across Providers

ProviderInput (per 1M)Output (per 1M)
Anthropic$10.00$50.00
AWS Bedrock$10.00$50.00
GCP Vertex AI$10.00$50.00
Microsoft Foundry$10.00$50.00
OpenRouter$10.00$50.00
View all 8 providers →

Pricing

TypePrice (per 1M)
Input tokens$10.00
Output tokens$50.00

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsPrompt CachingBatch API

About Claude Fable 5

Anthropic's most capable widely released model, built for demanding reasoning and long-horizon agentic work. Claude Fable 5 is the generally available Mythos-class Claude model, supports vision, tool use, structured outputs, prompt caching, Batch API processing, adaptive thinking that is always on, a 1M-token context window, and up to 128k output tokens. It launched on the Claude API, AWS Bedrock, Vertex AI, and Microsoft Foundry on June 9, 2026 with first-party pricing at $10 per 1M input tokens and $50 per 1M output tokens. Anthropic temporarily disabled Fable 5 access on June 12, 2026 after a US export control directive and redeployed Fable 5 and Mythos 5 on July 1, 2026.

FAQ

What does Claude Fable 5 cost on Replicate API?

On Replicate API, Claude Fable 5 costs $10.00 per 1M input tokens and $50.00 per 1M output tokens.

What is the context window for Claude Fable 5 on Replicate API?

Claude Fable 5 supports a 1m token context window on Replicate API.

How does Replicate API compare to other Claude Fable 5 providers?

Claude Fable 5 is available from 8 providers. The cheapest input pricing is $10.00/1M tokens from Anthropic.

What API model ID do I use for Claude Fable 5 on Replicate API?

Use the model ID anthropic/claude-fable-5 when calling Replicate API's API.

Who created Claude Fable 5?

Claude Fable 5 was created by Anthropic as part of the Claude Fable model family.

Is Claude Fable 5 open source?

Claude Fable 5 is not open source; the seed data lists it as proprietary.

Get Started