Claude Fable 5 API — pricing, playground & code

Name: Claude Fable 5 API
Brand: Anthropic

Overview

About Claude Fable 5

Claude Fable 5 is Anthropic's first Mythos-class model — a new tier above Opus, built for the hardest reasoning, research, and agentic work. Through CompanyFabric it runs behind the same OpenAI-compatible key as the rest of the Claude family, so escalating a task from Sonnet to Fable is a model-string change, not a new integration. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope — one integration covers the entire library.

Facts

At a glance

Availability

Live

Pricing

$6/Mtok in

Metered exactly per call

Context window

200k tokens

Commercial use

See license

Commercial use of outputs permitted per Anthropic's usage policies.

Variants

All endpoints

Claude Sonnet 4.5

$3/Mtok in

Frontier-quality text and reasoning through one OpenAI-compatible endpoint.

Chat Completions

Claude Haiku 4.5

$1/Mtok in

Fast, cheap frontier-family model for high-volume tasks.

Chat Completions

Claude Opus 4.6

$15/Mtok in

The frontier tier for the hardest reasoning and agentic work.

Chat Completions

Claude Fable 5

$6/Mtok in

Anthropic's first Mythos-class model — the new flagship tier above Opus, tuned for the hardest reasoning and agentic work.

Chat Completions

Claude Opus 5

$12/Mtok in

The Claude 5 generation's deep-work model — maximum-capability reasoning for research, architecture, and hard agentic tasks.

Chat Completions

Quickstart

How to use the Claude Fable 5 API

1
Create a free CompanyFabric account — starter credits are included, no card required.
2
Copy your API key from the dashboard. One key covers every model in the library.
3
Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "anthropic/claude-fable-5".
4
Read the exact metered cost of the call from the response — the same number shown in the playground.

Use cases

What teams build with it

Frontier agent loops

The model you reach for when the agent must not be wrong — long multi-step plans, architecture decisions, high-stakes tool chains.

agentsreasoningfrontier

Escalation tier

Route routine turns to Sonnet or Haiku and escalate the hard 5% to Fable — the routing split is one config line on one balance.

model routingescalation

Research & synthesis

Deep document analysis and cross-source synthesis where reasoning depth beats speed.

researchanalysis

Get better output

Prompting tips

Give it the whole problem, not a decomposition — Fable-class models plan better than most humans decompose.
Budget output generously on hard tasks; cutting reasoning short is the main failure mode users cause.
Reserve it for the calls that matter and meter the difference — per-key usage shows exactly what the top tier buys you.

Exact, metered, prepaid

Claude Fable 5 pricing

Claude Fable 5 pricing is per token: $6 / M input · $30 / M output. Output tokens cost 5× input tokens, so long generations — not long prompts — are what actually drive most bills. A typical call with a 2k-token prompt and a 1k-token answer costs about $0.0420.

Every call is metered exactly and attributed to your key — the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap, and bring your own provider key (BYOK) at 0% platform fee if you already have a direct contract.

Endpoint	Type	Price
Claude Sonnet 4.5	Chat	$3 / M input · $15 / M output
Claude Haiku 4.5	Chat	$1 / M input · $5 / M output
Claude Opus 4.6	Chat	$15 / M input · $75 / M output
Claude Fable 5	Chat	$6 / M input · $30 / M output
Claude Opus 5	Chat	$12 / M input · $60 / M output

Starter credits

Use Claude Fable 5 free

Your CompanyFabric starter credits cover your first Claude Fable 5 calls at no cost — create a free account, no card required, and the credits apply to Claude Fable 5 and every other model on the key. When they run out, prepaid credits or BYOK (0% fee) take over with no plan to pick.

All ways to use AI models free →

Production-grade

Code samples

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.companyfabric.com/v1",
  apiKey: process.env.COMPANYFABRIC_API_KEY,
})

const res = await client.chat.completions.create({
  model: "anthropic/claude-fable-5",
  max_tokens: 1024,
  temperature: 0.7,
  messages: [{ role: "user", content: "Say hello from the fabric." }],
})

console.log(res.choices[0].message.content)

Playground

Try it in the browser

Playground$6 in / $30 out per 1M tokens

Model

Max output

Prompt

Comparisons

Claude Fable 5 vs the alternatives

Claude Fable 5 vs GPT-5.5

Both sit at the top of their families. GPT-5.5 is priced aggressively on input tokens; Fable 5 is the pick where tool-use reliability and long-horizon agentic work decide the outcome. Behind one key, the honest answer is: run your own eval — switching is a string.

FAQ

Frequently asked questions

How much does the Claude Fable 5 API cost?

$6 / M input · $30 / M output. Every call is metered exactly and shown before you run it.

How do I get a Claude Fable 5 API key?

Create a CompanyFabric account, and one key unlocks Claude Fable 5 and every other model in the library. Free starter credits are included — no subscription, no card required to try it.

Why use Claude Fable 5 on CompanyFabric instead of going direct?

One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.

Is the API OpenAI-compatible?

Yes — point any OpenAI SDK at api.companyfabric.com/v1 and set model to "anthropic/claude-fable-5".

Can I use the output commercially?

Commercial use of outputs permitted per Anthropic's usage policies.

How does billing work?

Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.

What is the difference between Claude Fable 5 and Claude Mythos 5?

They share the same underlying model. Fable 5 is the generally available variant with additional safety measures for dual-use capabilities; Mythos 5 is available only to approved organizations. The gateway serves Fable 5.

Fable 5 or Opus 5 — which should I default to?

Opus 5 is the deep-work model of the Claude 5 generation; Fable 5 sits above it as the new flagship tier. Start with Opus 5 for heavy analysis and step up to Fable 5 where results still fall short — both are one string apart on the same key.

Provider

About Anthropic

Anthropic publishes the claude family. Also in this family: Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.6, Claude Opus 5. License: Commercial use of outputs permitted per Anthropic's usage policies.

Explore

Related model APIs

GPT-5.5

$5/Mtok in

OpenAI

OpenAI's flagship, one key away.

text

DeepSeek V4

$0.3/Mtok in

DeepSeek

Open-weight frontier-adjacent reasoning at commodity prices.

text

Gemini 3.7 Flash

Google

Google's current fast model, million-token context.

text

Gemini 3.5 Flash

Google

The previous stable Flash, still current for most work.

text

Gemini 2.5 Pro

Google

Google's stable Pro tier — the non-preview reasoning model.

text

Gemini 2.5 Flash

Google

Long-context workhorse on the stable 2.5 line.

text

Browse all models A–Z →

One key. Every model. Exact prices.

Run Claude Fable 5 with free starter credits. Free starter credits included — no subscription required.

Get your API key Browse all models