Question 1

What is Claude Fable 5?

Accepted Answer

Claude Fable 5 is a model from Anthropic, released on Jun 9, 2026. Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins. It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Question 2

How much does Claude Fable 5 cost?

Accepted Answer

On the Respan gateway, input starts at $10.00 per 1M tokens on every provider, and output starts at $50.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve Claude Fable 5 on Respan?

Accepted Answer

6 providers serve Claude Fable 5: Anthropic, DeepInfra, OpenRouter, Perplexity, Tera, and Google Vertex AI. Perplexity, Tera, and Google Vertex AI require your own provider API key (BYOK).

Question 4

What is Claude Fable 5's context window?

Accepted Answer

Claude Fable 5 accepts up to 1M tokens of context on its largest provider route.

Question 5

How do I use Claude Fable 5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-fable-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Claude Fable 5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 803 tokens per second, and the lowest response latency was 4.1 seconds on Anthropic. Speed varies with request size and provider.

Question 7

Where does Claude Fable 5 rank on the Respan Index?

Accepted Answer

Claude Fable 5 scores 62.2 out of 100 on the Respan Index v1.1, ranking #9 of 138 models. By category: Coding 57.2, Agents 67.9, Reasoning 60.9, Knowledge & language 72.4, and Human preference 56.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Claude Fable 5 score on benchmarks?

Accepted Answer

Claude Fable 5 has 44 published benchmark scores, including SWE-bench Verified 95%, OSWorld-Verified 86%, and LiveBench Reasoning 89.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
Anthropic`anthropic/claude-fable-5`	1M	$10.00/M	$50.00/M
DeepInfra`deepinfra/anthropic/claude-fable-5`	1M	$10.00/M	$50.00/M
OpenRouter`openrouter/anthropic/claude-fable-5`	1M	$10.00/M	$50.00/M
PerplexityBYOK only`perplexity/anthropic/claude-fable-5`	1M	$10.00/M	$50.00/M
TeraBYOK only`tera/anthropic/claude-fable-5`	200K	$10.00/M	$50.00/M
Google Vertex AIBYOK only`vertex_ai/claude-fable-5@default`	1M	$10.00/M	$50.00/M

Claude Fable 5

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding13

Apps

Claude Fable 5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Agents9

Reasoning7

Math4

Knowledge3

Multimodal1

Arena4

Other3