Start free

Claude · Fast / Budget · 200K context window

Claude Haiku 4.5 pricing for intent detection

$0.000800 per call at 300 input / 100 output tokens.

Per call

$0.000800

10K calls/mo

$8

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 intent detection spend. Pricing updated weekly.

Configure your usage

300
100100K
100
5050K
10,000
1001M

Estimated cost

Monthly cost
$8
10,000 calls/month
Cost per call$0.000800
Daily cost$0.2667
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=100,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.000800 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 intent detection benchmarks. Hover for details.

Gemini 3.5 Flash-Lite$0.000225Gemini 3 Flash$0.000450Claude Haiku 4.5$0.000800GPT 5.6 Luna$0.000900Gemini 3.5 Flash$0.001350Claude Sonnet 5$0.001600Gemini 3.1 Pro$0.001800GPT 5.4$0.002250GPT 5.6 Terra$0.002250Claude Sonnet 4.6$0.002400Claude Opus 4.8$0.004000GPT 5.5$0.004500GPT 5.6 Sol$0.004500Claude Fable 5$0.008000

Cheapest viable option: Gemini 3.5 Flash-Lite at $0.000225/call (72% less, 85/100 quality).

Complete Claude Haiku 4.5 pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$1.00300
Output$5.00100

Prompt caching: 90% off input tokens

Caching drops input cost from $1.00 to $0.10/MTok. For repeated system prompts, that saves $0.000270 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$0.000800$8$5.3$2.7
50,000 calls$0.000800$40$26.5$13.5
100,000 calls$0.000800$80$53$27
500,000 calls$0.000800$400$265$135
1,000,000 calls$0.000800$800$530$270

Claude Haiku 4.5 quality benchmarks for intent detection

Use Claude Haiku 4.5 for intent detection

Scores 90/100 (rank #2 of 14). Strong pick for production intent detection workloads.

Top-ranked: Gemini 3.5 Flash (92/100) at $0.001350/call

Performance across all task types

Claude Haiku 4.5 scores by task type. Intent Detection highlighted.

Classification *90Extraction88Q&A86Summarization82Code Generation72Code Review70Reasoning65Creative Writing60
Task typeConfidence scoreRank out of 14
Classification(current page)90/100#2
Extraction88/100#2
Q&A86/100#4
Summarization82/100#5
Code Generation72/100#6
Code Review70/100#7
Reasoning65/100#7
Creative Writing60/100#7

Alternative models for intent detection

13 models score 80+ on intent detection benchmarks, sorted by input rate. Cheapest: Gemini 3.5 Flash-Lite (72% less, 85/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs Claude
Gemini 3.5 Flash-LiteGemini$0.25$1.5085/100$0.00022572% cheaper
Gemini 3 FlashGemini$0.50$3.0088/100$0.00045044% cheaper
GPT 5.6 LunaGPT$1.00$6.0091/100$0.00090013% more
Gemini 3.5 FlashGemini$1.50$9.0092/100$0.00135069% more
Claude Sonnet 5Claude$2.00$10.0086/100$0.001600100% more
Gemini 3.1 ProGemini$2.00$12.0086/100$0.001800125% more
GPT 5.4GPT$2.50$15.0088/100$0.002250181% more
GPT 5.6 TerraGPT$2.50$15.0089/100$0.002250181% more
Claude Sonnet 4.6Claude$3.00$15.0084/100$0.002400200% more
Claude Opus 4.8Claude$5.00$25.0080/100$0.004000400% more
GPT 5.5GPT$5.00$30.0085/100$0.004500462% more
GPT 5.6 SolGPT$5.00$30.0086/100$0.004500462% more
Claude Fable 5Claude$10.00$50.0082/100$0.008000900% more

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$25.00200K
Claude Sonnet 4.6Mid-tier$3.00$15.00200K
Claude Sonnet 5Mid-tier$2.00$10.00200K
Claude Fable 5Flagship$10.00$50.001,000K

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

Invoice Parsing

$0.005000/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

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 intent detection per API call?

$0.000800 per call at 300 input / 100 output tokens.

Is Claude Haiku 4.5 the best model for intent detection?

Scores 90/100, rank #2 of 14 models. Top-ranked: Gemini 3.5 Flash at 92/100.

What is the cheapest model for intent detection with good quality?

Gemini 3.5 Flash-Lite scores 85/100 quality at $0.25/$1.50 per MTok. That is 72% less than Claude Haiku 4.5 per call.

How can I reduce my Claude Haiku 4.5 costs for intent detection?

Three strategies: prompt caching (90% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.000800 drops to about $0.000040 per call.

How does Claude Haiku 4.5 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 Sonnet 5 at $2.00/$10.00, Claude Fable 5 at $10.00/$50.00.

What context window does Claude Haiku 4.5 support?

200K tokens total. Typical intent detection calls use 300 plus 100 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