ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Anthropic
Proprietary API Anthropic · claude-fable-5 · Text+Image+PDF

Claude Fable 5 Official Specifications, Pricing & Benchmarks

First-gen Anthropic Fable ultra-flagship scoring 63.0% on HLE-Full (w/ Tools) and 92.6% on GPQA Diamond.

📋 Claude Fable 5 Official API & System Card Specifications

Verified against official Anthropic developer documentation & pricing

API Model ID: claude-fable-5

1. Identity & Capabilities

API Spec
API Model ID
claude-fable-5
Release Date
2026-06-07
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
128,000 tokens
Input Modalities
Text + Image + PDF
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 10
Cached Input / 1M
$ 1 -90%
Output / 1M Tokens
$ 50

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1534 AA Index 59
🧠 Reasoning
GPQA Diamond 92.6 %

PhD-level Google-proof science reasoning questions

🧠 Reasoning
HLE-Full (w/ Tools) 63 %

Full multimodal Humanity's Last Exam with tools

📚 Knowledge
AA-LCR 70 %

Agent Arena Long Context Reasoning benchmark.

🧠 Reasoning
CritPt 28.6 %

CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=1 top_p=0.95 max_tokens=65,536

💡 Custom temperature disabled in reasoning mode; adjust reasoning effort/budget instead.

📊 Claude Fable 5 Full Benchmark Scorecard

19 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 9 items

SWE-Bench Verified #1/59 95%

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

FrontierSWE #1/16 90%

FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

Terminal-Bench 2.1 #13/37 84.3%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

SWE-Bench Pro #4/52 80%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

ExploitBench #4/11 78%

ExploitBench is a cybersecurity benchmark that evaluates a model's ability to discover and exploit software vulnerabilities, reported as the fraction of challenges where the model captures the target (Cap%).

DeepSWE 1.1 #17/49 70%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

FrontierCode 1.1 #2/23 53.5%

FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

FrontierCode #3/4 46.3%

FrontierCode is Cognition's coding evaluation that tests whether models can pass difficult coding tasks while meeting the standards of high-quality production codebases. The Diamond subset contains the hardest problems.

Terminal-Bench 4.0 #12/31 44.5%

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Claude Fable 5

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Claude Fable 5 open-source or proprietary?

Claude Fable 5 (claude-fable-5) is a proprietary commercial model by Anthropic. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Claude Fable 5?

Claude Fable 5 supports 1000K input context and 128,000 max output tokens, priced at $10/1M input ($1/1M cached) and $50/1M output.