Anthropic

Claude Fable 5 — Benchmark Scores, Pricing & Performance Analysis

FLAGSHIPAnthropic
Output Speed
60 tok/s
Input Cost
$10.0/1M
Output Cost
$50.0/1M
Context Window
1.0M
Max Output
128K
Accepts
text, image, file

Claude Fable 5 by Anthropic demonstrates excellent coding ability. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
49.74th of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

AA Coding Index
76.57th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Design Arena ELO
13346th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
Website Arena ELO
130910th of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)
SWE-bench Verified
95.0%1st of 67

Real-world software engineering task resolution

swebench.com

Reasoning Benchmarks

τ²-Bench Airline
80.2%2nd of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)
GPQA Diamond
83.8%41st of 140

Graduate-level science Q&A by domain experts

Papers
AA Agentic Index
517th of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)

Speed Benchmarks

Time to First Token
81680 ms92nd of 92

Latency before first token arrives

Aggregated
Output Speed
60 tok/s65th of 94

Tokens generated per second

Aggregated

Cost Benchmarks

Cached Input Cost
$1.0131st of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API
Input Cost
$10.0394th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$50.0397th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
1.0M52nd of 451

Maximum context window size

OpenRouter API

Available from 37 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Kenari$0$0—1.0M—
Xpersona$3$18.5$0.31.0M—
302.AI$10$50—1.0M—
Abacus$10$50—1.0M—
Amazon Bedrock$10$50$11.0MSupported
Anthropic$10$50$11.0MSupported
Azure$10$50$11.0MSupported
Azure Cognitive Services$10$50$11.0M—
Cloudflare AI Gateway$10$50$11.0M—
CrossModel$10$50$11.0M—
DevPass (LLM Gateway)$10$50$11.0M—
Eden AI$10$50$11.0M—
FreeModel$10$50$11.0M—
GitHub Copilot$10$50$11.0M—
Impossibl$10$50$11.0M—
Kilo Gateway$10$50$11.0M—
LLM Gateway$10$50$11.0M—
Merge Gateway$10$50$11.0M—
Modelis$10$50—1.0M—
NanoGPT$10$50$11.0M—
Neon$10$50$11.0M—
Ofox$10$50$11.0M—
OpenCode Zen$10$50$11.0M—
OpenRouter$10$50$11.0MSupported
Opper$10$50$11.0M—
OrcaRouter$10$50$11.0M—
Requesty$10$50$11.0M—
Vercel AI Gateway$10$50$11.0MSupported
Vertex$10$50$11.0MSupported
Vertex (Anthropic)$10$50$11.0M—
Vivgrid$10$50$1.251.0M—
ZenMux$10$50$11.0M—
AIHubMix$11$55$1.11.0M—
Pioneer$11$55$1.11.0M—
Venice AI$12$60$1.21.0M—
Model Oracle AI———1.0M—
Snowflake Cortex———1.0M—

Claude Fable 5 — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Claude Fable 5 — Frequently Asked Questions

How much does Claude Fable 5 cost?

Claude Fable 5 costs $10.0 per 1M input tokens and $50.0 per 1M output tokens. This places it in the premium pricing tier.

How fast is Claude Fable 5?

Claude Fable 5 generates output at 60 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 81680 ms.

How good is Claude Fable 5 at coding?

Claude Fable 5 achieves 95.0% on SWE-bench Verified, demonstrating excellent real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.

What is the context window of Claude Fable 5?

Claude Fable 5 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Claude Fable 5?

Claude Fable 5 was created by Anthropic. It is classified as a flagship model in our catalogue.

Is Claude Fable 5 open source?

No, Claude Fable 5 is a proprietary model. It is available through Anthropic's API and compatible providers.