Start free

Claude · Flagship · 1,000K context window

Claude Fable 5 pricing for json extraction

$0.0700 per call at 3,000 input / 800 output tokens.

Per call

$0.0700

10K calls/mo

$700

Cache savings

90% off input

Batch savings

50% off all

Calculate your Claude Fable 5 costs

Adjust token counts, volume, and discount toggles to model your json extraction spend. Pricing updated weekly.

Configure your usage

3,000
100100K
800
5050K
10,000
1001M

Estimated cost

Monthly cost
$700
10,000 calls/month
Cost per call$0.07
Daily cost$23
Input rate$10.00/MTok
Output rate$50.00/MTok
Analyze your real spend

Quick start

Call Claude Fable 5 with the Anthropic Python SDK:

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-fable-5",
    max_tokens=800,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0700 per call at standard rates
# Input:  $10.00/MTok
# Output: $50.00/MTok

How Claude Fable 5 compares on cost

Per-call cost for all models scoring 50+ on json extraction benchmarks. Hover for details.

Gemini 3.5 Flash-Lite$0.001950Gemini 3 Flash$0.003900Claude Haiku 4.5$0.007000GPT 5.6 Luna$0.007800Gemini 3.5 Flash$0.0117Claude Sonnet 5$0.0140Gemini 3.1 Pro$0.0156GPT 5.4$0.0195GPT 5.6 Terra$0.0195Claude Sonnet 4.6$0.0210Claude Opus 4.8$0.0350GPT 5.5$0.0390GPT 5.6 Sol$0.0390Claude Fable 5$0.0700

Cheapest viable option: Gemini 3.5 Flash-Lite at $0.001950/call (97% less, 83/100 quality).

Complete Claude Fable 5 pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$10.003,000
Output$50.00800

Prompt caching: 90% off input tokens

Caching drops input cost from $10.00 to $1.00/MTok. For repeated system prompts, that saves $0.0270 per call.

Batch API: 50% off all tokens

Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.

Monthly cost projections

Monthly volumeCost per callStandard monthlyCached monthlyYou save with caching
10,000 calls$0.0700$700$430$270
50,000 calls$0.0700$3,500$2,150$1,350
100,000 calls$0.0700$7,000$4,300$2,700
500,000 calls$0.0700$35,000$21,500$13,500
1,000,000 calls$0.0700$70,000$43,000$27,000

Claude Fable 5 quality benchmarks for json extraction

Claude Fable 5 is a solid pick for json extraction

Scores 85/100 (rank #4 of 14). Good balance of quality and cost for json extraction.

Top-ranked: GPT 5.6 Terra (90/100) at $0.0195/call

Performance across all task types

Claude Fable 5 scores by task type. JSON Extraction highlighted.

Reasoning98Code Generation96Code Review95Creative Writing95Summarization90Q&A88Extraction *85Classification82
Task typeConfidence scoreRank out of 14
Reasoning98/100#1
Code Generation96/100#1
Code Review95/100#1
Creative Writing95/100#1
Summarization90/100#3
Q&A88/100#4
Extraction(current page)85/100#4
Classification82/100#5

Alternative models for json extraction

13 models score 80+ on json extraction benchmarks, sorted by input rate. Cheapest: Gemini 3.5 Flash-Lite (97% less, 83/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs Claude
Gemini 3.5 Flash-LiteGemini$0.25$1.5083/100$0.00195097% cheaper
Gemini 3 FlashGemini$0.50$3.0086/100$0.00390094% cheaper
Claude Haiku 4.5Claude$1.00$5.0088/100$0.00700090% cheaper
GPT 5.6 LunaGPT$1.00$6.0089/100$0.00780089% cheaper
Gemini 3.5 FlashGemini$1.50$9.0090/100$0.011783% cheaper
Claude Sonnet 5Claude$2.00$10.0088/100$0.014080% cheaper
Gemini 3.1 ProGemini$2.00$12.0085/100$0.015678% cheaper
GPT 5.4GPT$2.50$15.0089/100$0.019572% cheaper
GPT 5.6 TerraGPT$2.50$15.0090/100$0.019572% cheaper
Claude Sonnet 4.6Claude$3.00$15.0086/100$0.021070% cheaper
Claude Opus 4.8Claude$5.00$25.0082/100$0.035050% cheaper
GPT 5.5GPT$5.00$30.0087/100$0.039044% cheaper
GPT 5.6 SolGPT$5.00$30.0088/100$0.039044% cheaper

About Claude Fable 5

Provider

Claude

Tier

Flagship

Context

1,000K tokens

Released

Jun 2026

Other models from Claude

ModelTierInput $/MTokOutput $/MTokContext
Claude Opus 4.8Flagship$5.00$25.00200K
Claude Sonnet 4.6Mid-tier$3.00$15.00200K
Claude Haiku 4.5Fast / Budget$1.00$5.00200K
Claude Sonnet 5Mid-tier$2.00$10.00200K

You can compare Claude Fable 5 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Claude Fable 5 pricing for other use cases

See how Claude Fable 5 costs change across different workload types.

Code Generation

$0.2200/call

Unit Test Generation

$0.2800/call

SQL Generation

$0.0650/call

API Generation

$0.3300/call

Code Refactoring

$0.2400/call

Code Review

$0.1500/call

PR Review

$0.2300/call

Security Review

$0.1850/call

Bug Detection

$0.1500/call

Document Summarization

$0.1500/call

PDF Summarization

$0.2250/call

Meeting Notes

$0.1800/call

Email Summarization

$0.0550/call

Chatbot

$0.0700/call

RAG Pipeline

$0.1350/call

Customer Support Bot

$0.0800/call

FAQ Bot

$0.0550/call

Data Extraction

$0.0900/call

Invoice Parsing

$0.0500/call

Resume Parsing

$0.0650/call

Chain of Thought

$0.2800/call

Legal Analysis

$0.3000/call

Math Reasoning

$0.1650/call

Financial Analysis

$0.2800/call

Content Moderation

$0.0100/call

Sentiment Analysis

$0.0100/call

Categorization

$0.0155/call

Intent Detection

$0.008000/call

Copywriting

$0.1050/call

Blog Writing

$0.4100/call

Marketing Copy

$0.1580/call

Product Descriptions

$0.0800/call

Related pages

Frequently asked questions

How much does Claude Fable 5 cost for json extraction per API call?

$0.0700 per call at 3,000 input / 800 output tokens.

Is Claude Fable 5 the best model for json extraction?

Scores 85/100, rank #4 of 14 models. Top-ranked: GPT 5.6 Terra at 90/100.

What is the cheapest model for json extraction with good quality?

Gemini 3.5 Flash-Lite scores 83/100 quality at $0.25/$1.50 per MTok. That is 97% less than Claude Fable 5 per call.

How can I reduce my Claude Fable 5 costs for json extraction?

Three strategies: prompt caching (90% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.0700 drops to about $0.003500 per call.

How does Claude Fable 5 pricing compare to other Claude models?

Claude also offers: Claude Opus 4.8 at $5.00/$25.00, Claude Sonnet 4.6 at $3.00/$15.00, Claude Haiku 4.5 at $1.00/$5.00, Claude Sonnet 5 at $2.00/$10.00.

What context window does Claude Fable 5 support?

1,000K tokens total. Typical json extraction calls use 3,000 plus 800 tokens, well within limits.

Track what you spend on AI

This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.

Free spend teardownStart free dashboard