Start free

Claude · Fast / Budget · 200K context window

Claude Haiku 4.5 pricing for invoice parsing

$0.005000 per call at 2,000 input / 600 output tokens.

Per call

$0.005000

10K calls/mo

$50

Cache savings

90% off input

Batch savings

50% off all

Calculate your Claude Haiku 4.5 costs

Adjust token counts, volume, and discount toggles to model your invoice parsing spend. Prices verified daily against provider pricing pages.

Configure your usage

2,000
100100K
600
5050K
10,000
1001M

Estimated cost

Monthly cost
$50
10,000 calls/month
Cost per call$0.005000
Daily cost$2
Input rate$1.00/MTok
Output rate$5.00/MTok
Analyze your real spend

Quick start

Call Claude Haiku 4.5 with the Anthropic Python SDK:

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-haiku-4-5",
    max_tokens=600,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.005000 per call at standard rates
# Input:  $1.00/MTok
# Output: $5.00/MTok

How Claude Haiku 4.5 compares on cost

Per-call cost for all models scoring 50+ on invoice parsing benchmarks. Hover for details.

GPT 6 Luna$0.000500GPT 5.6 Luna$0.001120GPT 5.4 Nano$0.001150Gemini 3.5 Flash-Lite$0.002100Gemini 3 Flash$0.002800Grok Build 0.1$0.003200Gemini 3.6 Flash$0.003750Gemini 3.7 Flash$0.003750Gemini 3.8 Flash$0.003750Grok 4.3$0.004000GPT 5.4 Mini$0.004200Claude Haiku 4.5$0.005000Grok 4.6$0.007600Grok 4.5$0.007600Grok 4.7$0.007600Gemini 3.5 Flash$0.008400Claude Sonnet 5$0.010000GPT 6 Sol$0.010000GPT 5.6 Terra$0.0112Gemini 3.1 Pro$0.0112GPT 5.4$0.0140Claude Sonnet 4.6$0.0150Claude Opus 5.5$0.0200GPT 5.6 Sol$0.0200Claude Opus 4.8$0.0250Claude Opus 5$0.0250Claude Opus 4.7$0.0250Claude Opus 4.6$0.0250GPT 5.5$0.0280Claude Fable 5.1$0.0500Claude Fable 5$0.0500GPT 6 Astra$0.0500

Cheapest viable option: Gemini 3 Flash at $0.002800/call (44% less, 86/100 quality).

What drives invoice parsing cost

Invoices are short, highly repetitive documents processed in bulk: the ideal batch API workload. Per-document cost is low; total cost is set by volume and by whether you are paying full rate for a job that could have run asynchronously overnight at a discount. The extraction schema is constant, so it should never be paying full input rate either.

For Claude Haiku 4.5 specifically, that means output tokens cost 5.0x more than input, at $5.00 vs $1.00 per MTok. At this use case’s 2,000/600 token split, output accounts for 60% of the $0.005000 per-call cost.

Complete Claude Haiku 4.5 pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$1.002,000
Output$5.00600

Prompt caching: 90% off input tokens

Caching drops input cost from $1.00 to $0.10/MTok. For repeated system prompts, that saves $0.001800 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$0.005000$50$32$18
50,000 calls$0.005000$250$160$90
100,000 calls$0.005000$500$320$180
500,000 calls$0.005000$2,500$1,600$900
1,000,000 calls$0.005000$5,000$3,200$1,800

Claude Haiku 4.5 quality benchmarks for invoice parsing

Use Claude Haiku 4.5 for invoice parsing

Scores 88/100 (rank #2 of 88). Strong pick for production invoice parsing workloads.

Performance across all task types

Claude Haiku 4.5 scores by task type. Invoice Parsing highlighted.

Classification90Extraction *88Q&A86Summarization82Code Generation72Code Review70Reasoning65Creative Writing60
Task typeConfidence scoreRank out of 88
Classification90/100#2
Extraction(current page)88/100#2
Q&A86/100#4
Summarization82/100#5
Code Generation72/100#6
Code Review70/100#7
Reasoning65/100#7
Creative Writing60/100#7

Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

Alternative models for invoice parsing

1 models score 80+ on invoice parsing benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (44% less, 86/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs Claude
Gemini 3 FlashGemini$0.50$3.0086/100$0.00280044% cheaper

About Claude Haiku 4.5

Provider

Claude

Tier

Fast / Budget

Context

200K tokens

Released

Oct 2025

Other models from Claude

ModelTierInput $/MTokOutput $/MTokContext
Claude Opus 4.8Flagship$5.00$25.001M
Claude Sonnet 4.6Mid-tier$3.00$15.001M
Claude Sonnet 5Mid-tier$2.00$10.001M
Claude Opus 5Flagship$5.00$25.001M
Claude Fable 5.1Flagship$10.00$50.001M
Claude Fable 5Flagship$10.00$50.001M
Claude Mythos 5.1Flagship$10.00$50.001M
Claude Mythos 5Flagship$10.00$50.001M
Claude Opus 4.7Flagship$5.00$25.001M
Claude Opus 4.6Flagship$5.00$25.001M
Claude Opus 4.5Flagship$5.00$25.00200K
Claude Opus 5.5Flagship$4.00$20.001M
Claude Sonnet 4.5Mid-tier$3.00$15.00200K
Claude Sonnet 5.5Mid-tier$2.00$10.001M
Claude Haiku 5.5Fast / Budget$0.10$0.501M

You can compare Claude Haiku 4.5 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 Haiku 4.5 pricing for other use cases

See how Claude Haiku 4.5 costs change across different workload types.

Code Generation

$0.0220/call

Unit Test Generation

$0.0280/call

SQL Generation

$0.006500/call

API Generation

$0.0330/call

Code Refactoring

$0.0240/call

Code Review

$0.0150/call

PR Review

$0.0230/call

Security Review

$0.0185/call

Bug Detection

$0.0150/call

Document Summarization

$0.0150/call

PDF Summarization

$0.0225/call

Meeting Notes

$0.0180/call

Email Summarization

$0.005500/call

Chatbot

$0.007000/call

RAG Pipeline

$0.0135/call

Customer Support Bot

$0.008000/call

FAQ Bot

$0.005500/call

Data Extraction

$0.009000/call

JSON Extraction

$0.007000/call

Resume Parsing

$0.006500/call

Chain of Thought

$0.0280/call

Legal Analysis

$0.0300/call

Math Reasoning

$0.0165/call

Financial Analysis

$0.0280/call

Content Moderation

$0.001000/call

Sentiment Analysis

$0.001000/call

Categorization

$0.001550/call

Intent Detection

$0.000800/call

Copywriting

$0.0105/call

Blog Writing

$0.0410/call

Marketing Copy

$0.0158/call

Product Descriptions

$0.008000/call

Related pages

Frequently asked questions

How much does Claude Haiku 4.5 cost for invoice parsing per API call?

A typical invoice parsing call using Claude Haiku 4.5 costs about $0.005000 per call. This estimate uses 2,000 input tokens and 600 output tokens at standard rates. Standard rates are $1.00 per million input tokens and $5.00 per million output tokens.

Is Claude Haiku 4.5 the best model for invoice parsing?

Claude Haiku 4.5 scores 88 out of 100 on invoice parsing benchmarks overall. It ranks #2 across all 88 models in our cross-provider registry. It is the top-ranked model for this task type across all four providers. Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

What is the cheapest model for invoice parsing with good quality?

The most affordable model for invoice parsing above 80/100 quality is Gemini 3 Flash. It comes from Gemini at $0.50 per million input tokens. Output costs $3.00 per million tokens with a quality score of 86/100. Switching from Claude Haiku 4.5 to Gemini 3 Flash saves about 44% per API call.

How can I reduce my Claude Haiku 4.5 costs for invoice parsing?

Three strategies lower Claude Haiku 4.5 costs for this task type effectively. Prompt caching gives a 90% discount on input tokens when reusing system prompts. The batch API gives 50% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.005000 to about $0.000250 per call.

How does Claude Haiku 4.5 pricing compare to other Claude models?

Claude has 15 other models alongside Claude Haiku 4.5 today: Claude Opus 4.8 at $5.00/$25.00 per million tokens (flagship), Claude Sonnet 4.6 at $3.00/$15.00 per million tokens (mid-tier), Claude Sonnet 5 at $2.00/$10.00 per million tokens (mid-tier), Claude Opus 5 at $5.00/$25.00 per million tokens (flagship), Claude Fable 5.1 at $10.00/$50.00 per million tokens (flagship), Claude Fable 5 at $10.00/$50.00 per million tokens (flagship), Claude Mythos 5.1 at $10.00/$50.00 per million tokens (flagship), Claude Mythos 5 at $10.00/$50.00 per million tokens (flagship), Claude Opus 4.7 at $5.00/$25.00 per million tokens (flagship), Claude Opus 4.6 at $5.00/$25.00 per million tokens (flagship), Claude Opus 4.5 at $5.00/$25.00 per million tokens (flagship), Claude Opus 5.5 at $4.00/$20.00 per million tokens (flagship), Claude Sonnet 4.5 at $3.00/$15.00 per million tokens (mid-tier), Claude Sonnet 5.5 at $2.00/$10.00 per million tokens (mid-tier), Claude Haiku 5.5 at $0.10/$0.50 per million tokens (fast / budget). The right choice depends on whether your invoice parsing workload prioritizes quality, cost, or speed.

What context window does Claude Haiku 4.5 support?

Claude Haiku 4.5 supports a context window of 200K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For invoice parsing, typical calls use 2,000 input and 600 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.

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