Anthropic
Anthropic
LLMProprietary Commercial API Verified Architecture & Specs$10/1M in · $50/1M out

Claude Fable 5.1

Flagship Mythos-class foundation model designed for complex software engineering, long-horizon multi-step reasoning, and autonomous agent workflows. Features native 1M context support, advanced self-verification, and enhanced front-end and tool-calling execution.

Technical Architecture & Execution Specifications
Architecture Overview

Claude Fable 5.1

Flagship Mythos-class foundation model designed for complex software engineering, long-horizon multi-step reasoning, and autonomous agent workflows. Features native 1M context support, advanced self-verification, and enhanced front-end and tool-calling execution.

Supported Modalities
textcodeimagevisiontools

Hardware & Execution ParametersLLM

Total Parameter CountUndisclosed
Active Parameters (MoE)Dense Architecture
Context Window Capacity1,000,000 tokens
Model Weights FootprintCloud Hosted API
Distribution LicenseProprietary Commercial API
Standard API Pricing (1M Tokens)$10 in / $50 out
Model Heritage & Evolutionary Lineage

Genealogical Graph & Evolutionary Provenance

Tracing foundational base architecture ancestry, architectural successors, scale siblings, and reasoning distillation derivatives.

Independent Foundation Checkpoint

Claude Fable 5.1 operates as an autonomous foundation model architecture without direct precursor derivatives in this catalog.

Root Architecture Node
AI Model Architecture & Intelligence

Architecture Engineering & Capability Deep-Dive

An objective architectural evaluation of Claude Fable 5.1 by Anthropic, analyzing underlying compute dynamics, memory constraints, and deployment economics.

Topology & Attention Mechanics

Utilizes a highly optimized hybrid reasoning mode with a toggleable thinking budget, tailored for high-density tool synthesis and exact state routing.

Architecture Type:Advanced Transformer

Evaluation Profile & Reasoning

Exhibits frontier-tier behavior in reasoning and coding. Excels in complex multi-file codebase understanding.

Domain Specialty:LLM

LLM Hardware Sizing & Serving

Served via scalable API endpoints guaranteeing high tokens-per-second concurrency and enterprise SLAs.

KV Cache Mgmt: PagedAttention / FlashAttention-3
Hosting Type:Proprietary Commercial API

Inference Economics & Workflows

Thinking budgets allow cost/latency control. Dominant in zero-shot agentic loops and massive automated refactoring tasks where accuracy is paramount.

Enterprise Fit:Production Ready
Production Trade-Offs & Capability Balance

Architectural Strengths vs. Considerations

An objective balance sheet analyzing the operational advantages and production constraints of deploying Claude Fable 5.1.

Key Architectural Strengths

  • Hybrid reasoning mode with toggleable thinking budget excels at high-density code and agentic tool synthesis.
  • Native computer use capabilities and precise JSON generation streamline autonomous agent loops.
  • Massive 1,000,000-token context allows full-repository and book-length ingestion.
  • Demonstrated gpqa evaluation score of 94.8% in verified benchmarks.

Operational Considerations

  • Advanced agentic capabilities (e.g. computer use) mandate rigorous sandbox isolation and strict IAM boundaries.
  • 128k+ token prefill stages become heavily compute-bound and balloon KV cache without PagedAttention chunking.
LLM Hardware Sizing & Runtime Compatibility

Inference Runtimes & Hardware Sizing

Deployment targets, inference engines, and memory requirements for Claude Fable 5.1.

Recommended Hardware Profile:
Cloud Hosted API (Zero Local VRAM)
Supported Inference Engines
Vendor REST API

Primary managed cloud endpoint

Official
OpenRouter

Unified multi-provider gateway

Supported
Amazon Bedrock / GCP

Private cloud enterprise integration

Enterprise
OpenAI SDK

Standard chat completions client

Compatible
Precision & Quantization Formats
Cloud PrecisionManaged Serving

Vendor-optimized floating point precision (FP8/BF16)

Prompt CachingPrefix Cache

Up to 50–90% cost reduction on repeated system prompts

LLM Benchmark Database & Performance Metrics

6 Tested

Standardized evaluation results across reasoning, agentic coding, computer use, and alignment.

Flagship Headline MetricsIndustry SOTA Standard
Coding & Software

SWE-bench-Pro

82.4%legacy_reported
0%100%
Coding & Software

SWE-bench-Verified

96.2%legacy_reported
0%100%
gpqa
legacy_reported
94.8%
swe bench
legacy_reported
96.2%
GPQA-Diamond
legacy_reported
94.8%
SWE-bench-Pro
legacy_reported
82.4%
TerminalBench-2.1
legacy_reported
89.5%
SWE-bench-Verified
legacy_reported
96.2%
Commercial Rates & Inference Costs

API & Deployment Pricing

Standard API consumption rates per million tokens as indexed from official laboratory pricing documentation.

Usage TierRate / Unit
Prompt / Input Tokens$10 / 1M tokens
Completion / Output Tokens$50 / 1M tokens
Inference Cost & ROI Engine
Official API Rate
Prompt / Input Volume:50M Tokens / mo
1M500M1,000M
Generated / Output Volume:10M Tokens / mo
1M250M500M
Estimated Monthly Spend
$1,000.00/ mo
Input (50M @ $10.00/1M):$500.00
Output (10M @ $50.00/1M):$500.00
Cloud GPU Breakeven Ratio
RunPod RTX 4090 ($316/mo)3.16x spend
Lambda 1x H100 ($1,800/mo)0.56x spend
Similar Frontier Models & Alternatives
Explore All Comparisons

Comparable Foundation Architectures

Alternative models in the LLM class with similar capabilities, context windows, or deployment profiles.

Swiss-aiLLM

Apertus 70B

Context:66k ctx
Parameters:70B
Input Rate:Free / Self-Host
MetaLLM

Llama 3.3 70B

Context:128k ctx
Parameters:70B Dense
Input Rate:$0/1M
OpenAIReasoning

GPT-6 Astra

Context:1049k ctx
Parameters:Undisclosed
Input Rate:$10/1M
Integration & Deployment
import os
from anthropic import Anthropic

client = Anthropic(api_key=os.environ.get("ANTHROPIC_KEY"))

response = client.messages.create(
    model="anthropic-claude-fable-5-1-20260901",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain quantum superposition in 2 sentences."}
    ]
)
print(response.content[0].text)
Frequently Asked Questions

Frequently Asked Questions about Claude Fable 5.1

Essential facts, architectural specs, hardware constraints, and pricing answers for Claude Fable 5.1.

Claude Fable 5.1 is a proprietary API model and cannot be run locally. It requires no local VRAM.

Primary Sources & Access Repositories

All technical specifications, parameter distributions, context architectures, and benchmark evaluations for Claude Fable 5.1 are audited against primary source release documentation, research whitepapers, and verified vendor API endpoints.

api id:claude-fable-5-1