Claude API Pricing | 2026 Anthropic API Costs & Money-Saving Tips Complete Guide

Prompt Caching Saves 90% -- Claude API's Most Underrated Money-Saving Weapon

You probably already know Claude is great at writing code.

But you might not know this: Claude API's Prompt Caching mechanism can slash the cost of repeated long System Prompts by 90%. If your application sends tens of thousands of API requests per day, this single feature can save you thousands of dollars per month.

Yet, over 70% of Claude API users haven't even enabled this feature.

This article covers everything you need to know about Anthropic's Claude API pricing structure, cost-effectiveness of the three models, and all the money-saving tips in one place.

Need a Claude API enterprise plan? Contact CloudInsight for exclusive enterprise discounts and Taiwan uniform invoices.

TL;DR

Claude API pricing as of July 2026 (input/output per million tokens): Fable 5 $10/$50, Opus 4.8 $5/$25, Sonnet 5 $2/$10 (introductory, ends 2026-08-31, then $3/$15), Haiku 4.5 $1/$5. Leverage Prompt Caching to save 90% and Batch API to save 50% for significant cost reductions.

Claude API Complete Pricing for All Models | How to Choose Between Fable 5, Opus, Sonnet & Haiku

Answer-First: As of July 2026, the most capable widely released model is Claude Fable 5 ($10/$50) and the flagship is Opus 4.8 ($5/$25). Sonnet 5 is the best choice for most enterprises — just $2/$10 during introductory pricing, but that rate only runs through 2026-08-31. For simple, high-volume tasks, Haiku 4.5 ($1/$5) offers the best value. (Source: Anthropic official pricing page)

Complete Pricing Table for Current Models

Model	Input (per million tokens)	Output (per million tokens)	Context Window	Positioning
Claude Fable 5	$10.00	$50.00	1M tokens	Most capable widely released model
Claude Mythos 5	$10.00	$50.00	1M tokens	Limited availability
Claude Opus 4.8	$5.00	$25.00	1M tokens	Flagship, strongest reasoning
Claude Opus 4.7 / 4.6 / 4.5	$5.00	$25.00	1M on 4.8 / 4.7 / 4.6	Previous-generation flagship
Claude Sonnet 5 (introductory, through 2026-08-31)	$2.00	$10.00	1M tokens	Enterprise workhorse, best value
Claude Sonnet 5 (standard, from 2026-09-01)	$3.00	$15.00	1M tokens	Same model, price reverts
Claude Sonnet 4.6 / 4.5	$3.00	$15.00	1M on 4.6	Previous-generation workhorse
Claude Haiku 4.5	$1.00	$5.00	See official pricing page	Lightweight & fast, bulk processing

⚠️ The Sonnet 5 discount has a deadline: Introductory pricing of $2/$10 runs only through 2026-08-31. From 2026-09-01 the standard rate of $3/$15 applies — a 50% increase on both input and output. If you run significant Sonnet 5 volume, re-forecast your September budget at 1.5x today.

Note: The above are standard prices. Actual costs are lower when using Prompt Caching and Batch API. The 1M-token context window is included and billed at standard rates — there is no long-context premium.

Outdated Prices That Still Get Quoted

Several figures circulating online (including in the previous version of this article) are now obsolete. Ignore them:

Model	Old price	Current status
Claude Opus 4.1	$15.00 / $75.00	Deprecated. Current Opus models (4.8/4.7/4.6/4.5) are $5/$25, not $15/$75
Claude Haiku 3.5	$0.80 / $4.00	Retired (still reachable on some cloud platforms). Current Haiku 4.5 is $1/$5
Claude Opus 4, Sonnet 4	—	Retired

In short: if a source lists Opus at $15/$75 or Haiku at $0.80/$4, that source is out of date.

Why Unit Price Alone Is Misleading: the New Tokenizer Adds ~30% Tokens

Opus 4.7 and later models (including Fable 5, Mythos 5, and Sonnet 5) use a new tokenizer. The same text produces roughly 30% more tokens on those models.

What that means in practice:

• Moving a workload from Opus 4.6 to Opus 4.8 keeps the same $5/$25 unit price, but the bill for identical input goes up because the token count is higher
• Comparing unit prices across generations is meaningless. Compare by running your actual text through each model's token count, then multiplying by the unit price
• Re-baseline your own prompts with the official token-counting endpoint before you go live

Extended Thinking Mode: Additional Billing

Claude's higher-tier models support deep reasoning (Extended Thinking / Adaptive Thinking). When enabled, the model performs longer reasoning before answering.

Billing Impact:

• Thinking tokens are billed at the Output token rate
• The parameters and controls for thinking mode differ by model generation and change over time — check the Anthropic documentation for what applies to the model you are using
• Enabling deep reasoning meaningfully increases output token consumption, so include it in your cost estimates

When is it worth enabling?

• Complex logical reasoning
• Multi-step math problems
• Mission-critical tasks requiring high accuracy

When is it unnecessary?

• Simple text generation
• Translation
• Format conversion

---

Fable 5 vs Opus vs Sonnet vs Haiku: Complete Cost-Effectiveness Analysis | Save Money by Choosing the Right Model

Answer-First: For an identical workload (10,000 input tokens, 2,000 output tokens), Haiku 4.5 costs $0.02, Sonnet 5 costs $0.04 at introductory pricing, Opus 4.8 costs $0.10, and Fable 5 costs $0.20. Sonnet 5 is enough for most enterprise work; reserve Opus 4.8 and Fable 5 for the hardest long-horizon reasoning.

On quality scores: A previous version of this article listed model quality ratings such as 9.5/10. Those numbers had no verifiable source and have been removed entirely. Judge model quality by testing on your own tasks — don't buy on someone else's score.

Cost per Call for an Identical Workload

Assumption: 10,000 input tokens and 2,000 output tokens per call, with no caching or batching.

Model	Input cost	Output cost	Total per call
Claude Fable 5 ($10/$50)	$0.10	$0.10	$0.20
Claude Opus 4.8 ($5/$25)	$0.05	$0.05	$0.10
Claude Sonnet 5, introductory ($2/$10)	$0.02	$0.02	$0.04
Claude Sonnet 5, standard from 9/1 ($3/$15)	$0.03	$0.03	$0.06
Claude Haiku 4.5 ($1/$5)	$0.01	$0.01	$0.02

How to verify: 10,000 tokens = 0.01M tokens times the input rate; 2,000 tokens = 0.002M tokens times the output rate.

Caveat: This table compares equal token counts. Fable 5, Opus 4.7 and later, and Sonnet 5 use the new tokenizer, which produces roughly 30% more tokens for the same text — factor that into your real bill.

Our Model Selection Recommendations

Use Fable 5 / Opus 4.8 for:

• Complex multi-step reasoning and long-horizon automation
• Analyzing documents over 50 pages
• High-quality output for critical content
• High-value tasks with sufficient budget

Use Sonnet 5 for (recommended for most enterprises):

• Daily text generation and editing
• General code writing
• Customer service chatbots
• Medium-length document processing

Use Haiku 4.5 for:

• High-volume text classification
• Simple format conversion
• Real-time chatbots (requiring fast responses)
• Budget-constrained personal projects

How does it compare to OpenAI models? See AI API Pricing Comparison Complete Guide and OpenAI API Pricing Full Breakdown.

---

Claude API Batch Processing & Prompt Caching Savings | Actual Cost Savings Calculated

Answer-First: Batch API cuts both input and output by 50%. Prompt Caching charges 0.1x standard input on a cache hit (90% savings), 1.25x to write the 5-minute cache, and 2x to write the 1-hour cache. For a customer service bot handling 10,000 conversations per day on Sonnet 5 introductory pricing, using both features together takes the monthly bill from $3,000 to roughly $690.

Batch API: 50% Discount Mechanism

Like OpenAI, Anthropic also offers a Batch API. The rules are simple:

• 50% off both input and output
• Processing completed within 24 hours
• Up to 100,000 requests per batch

Batch API Pricing (standard price x 0.5):

Model	Batch Input (per million tokens)	Batch Output (per million tokens)
Fable 5	$5.00	$25.00
Opus 4.8	$2.50	$12.50
Sonnet 5 (introductory, through 2026-08-31)	$1.00	$5.00
Sonnet 5 (from 2026-09-01)	$1.50	$7.50
Haiku 4.5	$0.50	$2.50

Prompt Caching: Save Up to 90%

This is Claude API's most powerful cost-saving feature, and a major advantage Anthropic has over OpenAI.

How it works (multipliers apply to that model's standard input rate):

• Cache write, 5-minute TTL: 1.25x
• Cache write, 1-hour TTL: 2x
• Cache hit: 0.1x — a 90% saving

Prompt Caching Pricing:

Model	Standard Input	Write, 5-min (1.25x)	Write, 1-hour (2x)	Cache hit (0.1x)
Fable 5	$10.00	$12.50	$20.00	$1.00
Opus 4.8	$5.00	$6.25	$10.00	$0.50
Sonnet 5 (introductory)	$2.00	$2.50	$4.00	$0.20
Sonnet 5 (from 9/1)	$3.00	$3.75	$6.00	$0.30
Haiku 4.5	$1.00	$1.25	$2.00	$0.10

Real Cost Savings Calculation Example

Scenario: A customer service bot using Claude Sonnet 5 at introductory pricing ($2/$10).

• System Prompt: 3,000 tokens
• User input per conversation: 500 tokens
• Output per conversation: 300 tokens
• 10,000 conversations per day, 30 days = 300,000 conversations per month

Monthly cost without savings features:

• System Prompt: 3,000 x 300,000 = 900M tokens x $2/M = $1,800
• User Input: 500 x 300,000 = 150M tokens x $2/M = $300
• Output: 300 x 300,000 = 90M tokens x $10/M = $900
• Monthly total: $3,000

Monthly cost with Prompt Caching (5-minute cache, rewritten once a day = 30 writes per month):

• Cache write: 3,000 x 30 = 0.09M tokens x $2.50/M ≈ $0.23
• Cache hits: 3,000 x 299,970 ≈ 899.91M tokens x $0.20/M ≈ $180
• User Input: $300 (unchanged)
• Output: $900 (unchanged)
• Monthly total: roughly $1,380

Add Batch API on top (if non-real-time is acceptable):

• All costs cut by 50%
• Monthly total: roughly $690

From $3,000 down to roughly $690 -- 77% savings.

⚠️ Recalculate for September: The Sonnet 5 standard rate of $3/$15 is exactly 1.5x the introductory rate, so every line above scales by 1.5 — $4,500 unoptimized, roughly $2,070 with Prompt Caching only, and roughly $1,035 with Batch API on top. The percentage saved stays at 77%, but the absolute bill is 50% higher.

---

Enterprise Claude API Procurement with CloudInsight

CloudInsight offers Claude API enterprise procurement services:

• Exclusive enterprise discounts, better than Anthropic's official pricing
• Assistance with Prompt Caching and Batch API setup to maximize savings
• Taiwan uniform invoices + Chinese technical support

Get an Enterprise Quote Now ->

---

Claude API Free Trial & Starter Plans | The Most Affordable Way to Get Started

Answer-First: Anthropic Console provides API trial credits on new account registration. They are sufficient for feature testing and prototype validation, but rate limits are strict and not suitable for production. The credit amount and rate-limit thresholds change by account tier — check the Anthropic official pricing / rate-limit pages and the figures shown in your own Console, rather than reusing fixed numbers circulating online.

Steps to Claim Trial Credits

1. Register an account in the Anthropic Console
2. Verify your email
3. The system issues trial credits automatically (amount per the official announcement)
4. Create an API Key on the API Keys page
5. Start calling the API

Free Tier Rate Limits

The free/trial tier caps RPM (requests per minute), TPM (tokens per minute), and daily requests, and not every model is available. Anthropic adjusts these thresholds periodically — sign in to the Console to see the limits that actually apply to your account.

Upgrading from Free to Paid

After adding a credit card and depositing funds, rate limits increase progressively based on deposit amount and cumulative spend (Anthropic's tier system). Check the official pages for each tier's threshold and RPM. These numbers change often, so we deliberately do not publish fixed values here — using stale ones would distort your procurement estimate.

Note for Taiwan users: Anthropic's support for Taiwan credit cards is less stable than OpenAI's. Many Taiwan developers report payment rejections. In such cases, purchasing through CloudInsight is the fastest solution.

For more free AI API options, see Free AI API Recommendations & Limitations.

---

FAQ: Claude API Pricing Common Questions

Is Claude API cheaper than ChatGPT API?

It depends on the model tier you choose. Comparing mid-tier models: Claude Sonnet 5 is $2/$10 during introductory pricing versus OpenAI's gpt-5.6-terra at $2.50/$15, so Claude is cheaper on both sides while the promotion lasts. From 2026-09-01 Sonnet 5 reverts to $3/$15, making input slightly more expensive and output identical. Factoring in Claude's 90% Prompt Caching savings, high-volume workloads usually still land cheaper on Claude. We recommend calculating based on your actual usage.

How do I enable Prompt Caching for Claude API?

Use the cache_control parameter in your API request to mark the System Prompt as cacheable. Writing the cache costs 1.25x the standard input rate for the 5-minute cache and 2x for the 1-hour cache; subsequent cache hits cost only 0.1x (a 90% saving). The default cache expires after 5 minutes without a new request — use the 1-hour cache for traffic with longer gaps.

Can I pay for Claude API in TWD (Taiwan dollars)?

Anthropic currently only accepts USD payments. Taiwan users can use Visa or Mastercard credit cards that support international transactions, but may incur foreign transaction fees (typically 1.5%). For a rough TWD figure, estimate about NT$32 per US dollar; the actual amount varies with the exchange rate and card fees. Purchasing through CloudInsight allows payment in TWD with uniform invoices.

Is Claude Opus worth it, or is Sonnet good enough?

Sonnet 5 is sufficient for most use cases. Opus 4.8 has clear advantages in complex reasoning, long-horizon automation, and ultra-long document analysis, at about 1.7x the cost of Sonnet 5's standard rate ($5/$25 versus $3/$15) — or about 2.5x during Sonnet 5's introductory period through 2026-08-31. Test with Sonnet 5 first, upgrade to Opus 4.8 if quality doesn't meet requirements, and reserve Fable 5 ($10/$50) for the hardest tasks. Many teams use Sonnet for daily work and switch to Opus only for critical tasks.

Does Claude API offer enterprise plans?

Yes. Anthropic offers Enterprise plans with higher rate limits, dedicated support, and SLA guarantees. Additionally, purchasing through resellers like CloudInsight provides additional volume discounts and local technical support.

---

Make Every Dollar Count with Claude API | Cost-Saving Strategy Summary

Claude API pricing is in the mid-to-upper range among the three major AI APIs. But it has two standout advantages: cache hits cost only 0.1x standard input (90% savings), and Fable 5, Opus 4.8/4.7/4.6, Sonnet 5, and Sonnet 4.6 include a 1M-token context window billed at standard rates.

Four actionable steps you can take right now:

1. Enable Prompt Caching -- If your System Prompt exceeds 1,000 tokens, this is a must
2. Use Batch API for non-real-time tasks -- An instant 50% savings with no reason not to use it
3. Choose models by task -- Don't run everything on Fable 5 or Opus; spend your budget wisely
4. Re-forecast your September budget -- Sonnet 5 introductory pricing ends 2026-08-31 and rates rise 50% on 2026-09-01

For a more comprehensive look at AI API cost optimization, see LLM API Cost Optimization Practical Guide.

For enterprise bulk Claude API purchases with more discount options, see AI API Enterprise Procurement Guide.

---

Get the Best Claude API Enterprise Plan Now

CloudInsight is a Taiwan-based AI API enterprise procurement agent:

• Claude API enterprise discounts, better than official pricing
• Prompt Caching + Batch API setup guidance
• Taiwan uniform invoices for hassle-free accounting
• Chinese real-time technical support

Get an Enterprise Quote Now -> | Join LINE for Instant Consultation ->

---

References

1. Anthropic - Claude API official pricing page: https://platform.claude.com/docs/en/about-claude/pricing (verified 2026-07-22)
2. Anthropic - Prompt Caching Documentation
3. Anthropic - Batch API Documentation
4. Anthropic - Rate Limits and Usage Tiers
5. Anthropic - Extended Thinking Documentation

Further Reading

• Latest pricing intel: Complete guide to Claude Fable 5 ($10 input / $50 output per MTok — 2x Opus 4.8)
• Fable 5 API Pricing Explained: Costs and Usage Scenarios