tokevenClaude · Fast / Budget · 1M context window
Claude Haiku 5.5 pricing for categorization
$0.000155 per call at 800 input / 150 output tokens.
Per call
$0.000155
10K calls/mo
$1.55
Cache savings
90% off input
Batch savings
50% off all
Calculate your Claude Haiku 5.5 costs
Adjust token counts, volume, and discount toggles to model your categorization spend. Prices verified daily against provider pricing pages.
Configure your usage
Estimated cost
Quick start
Call Claude Haiku 5.5 with the Anthropic Python SDK:
from anthropic import Anthropic
client = Anthropic()
response = client.messages.create(
model="claude-haiku-5-5",
max_tokens=150,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.000155 per call at standard rates
# Input: $0.10/MTok
# Output: $0.50/MTokHow Claude Haiku 5.5 compares on cost
Per-call cost for all models scoring 50+ on categorization benchmarks. Hover for details.
Highest-quality affordable option: GPT 5.6 Luna at $0.000340/call (2.2x the cost, 91/100 quality). Claude Haiku 5.5 is already the cheapest choice for categorization.
What drives categorization cost
Classification into a fixed taxonomy is token-efficient by construction: the taxonomy is the same on every call and the output is one label. Put the taxonomy in the cached prefix and the marginal cost per item approaches the cost of the item text alone. Model tier matters less here than in any other use case tracked.
For Claude Haiku 5.5 specifically, that means output tokens cost 5.0x more than input, at $0.50 vs $0.10 per MTok. At this use case’s 800/150 token split, output accounts for 48% of the $0.000155 per-call cost.
Complete Claude Haiku 5.5 pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $0.10 | 800 |
| Output | $0.50 | 150 |
Prompt caching: 90% off input tokens
Caching drops input cost from $0.10 to $0.01/MTok. For repeated system prompts, that saves $0.000072 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 volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.000155 | $1.55 | $0.8300 | $0.7200 |
| 50,000 calls | $0.000155 | $7.75 | $4.15 | $3.6 |
| 100,000 calls | $0.000155 | $15.5 | $8.3 | $7.2 |
| 500,000 calls | $0.000155 | $77.5 | $41.5 | $36 |
| 1,000,000 calls | $0.000155 | $155 | $83 | $72 |
Claude Haiku 5.5 quality benchmarks for categorization
Benchmark data for categorization is pending for Claude Haiku 5.5. Test against your own evaluation suite before moving to production.
Benchmark data is not yet available for Claude Haiku 5.5. We recommend testing against your own evaluation criteria.
Alternative models for categorization
12 models score 80+ on categorization benchmarks, sorted by input rate. Cheapest: GPT 5.6 Luna (119% more, 91/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Claude |
|---|---|---|---|---|---|---|
| GPT 5.6 Luna | GPT | $0.20 | $1.20 | 91/100 | $0.000340 | 119% more |
| Gemini 3.5 Flash-Lite | Gemini | $0.30 | $2.50 | 85/100 | $0.000615 | 297% more |
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 88/100 | $0.000850 | 448% more |
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 90/100 | $0.001550 | 900% more |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 92/100 | $0.002550 | 1545% more |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 86/100 | $0.003100 | 1900% more |
| GPT 5.6 Terra | GPT | $2.00 | $12.00 | 89/100 | $0.003400 | 2094% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 86/100 | $0.003400 | 2094% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 88/100 | $0.004250 | 2642% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 84/100 | $0.004650 | 2900% more |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 86/100 | $0.006200 | 3900% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 85/100 | $0.008500 | 5384% more |
About Claude Haiku 5.5
Provider
Claude
Tier
Fast / Budget
Context
1M tokens
Released
Oct 2026
Added by the model-onboarding job on 2026-10-08. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date from the provider model list. Not yet benchmarked, so never recommended.
Other models from Claude
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Claude Opus 4.8 | Flagship | $5.00 | $25.00 | 1M |
| Claude Sonnet 4.6 | Mid-tier | $3.00 | $15.00 | 1M |
| Claude Haiku 4.5 | Fast / Budget | $1.00 | $5.00 | 200K |
| Claude Sonnet 5 | Mid-tier | $2.00 | $10.00 | 1M |
| Claude Opus 5 | Flagship | $5.00 | $25.00 | 1M |
| Claude Fable 5.1 | Flagship | $10.00 | $50.00 | 1M |
| Claude Fable 5 | Flagship | $10.00 | $50.00 | 1M |
| Claude Mythos 5.1 | Flagship | $10.00 | $50.00 | 1M |
| Claude Mythos 5 | Flagship | $10.00 | $50.00 | 1M |
| Claude Opus 4.7 | Flagship | $5.00 | $25.00 | 1M |
| Claude Opus 4.6 | Flagship | $5.00 | $25.00 | 1M |
| Claude Opus 4.5 | Flagship | $5.00 | $25.00 | 200K |
| Claude Opus 5.5 | Flagship | $4.00 | $20.00 | 1M |
| Claude Sonnet 4.5 | Mid-tier | $3.00 | $15.00 | 200K |
| Claude Sonnet 5.5 | Mid-tier | $2.00 | $10.00 | 1M |
You can compare Claude Haiku 5.5 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 5.5 pricing for other use cases
See how Claude Haiku 5.5 costs change across different workload types.
Code Generation
$0.002200/call
Unit Test Generation
$0.002800/call
SQL Generation
$0.000650/call
API Generation
$0.003300/call
Code Refactoring
$0.002400/call
Code Review
$0.001500/call
PR Review
$0.002300/call
Security Review
$0.001850/call
Bug Detection
$0.001500/call
Document Summarization
$0.001500/call
PDF Summarization
$0.002250/call
Meeting Notes
$0.001800/call
Email Summarization
$0.000550/call
Chatbot
$0.000700/call
RAG Pipeline
$0.001350/call
Customer Support Bot
$0.000800/call
FAQ Bot
$0.000550/call
Data Extraction
$0.000900/call
JSON Extraction
$0.000700/call
Invoice Parsing
$0.000500/call
Resume Parsing
$0.000650/call
Chain of Thought
$0.002800/call
Legal Analysis
$0.003000/call
Math Reasoning
$0.001650/call
Financial Analysis
$0.002800/call
Content Moderation
$0.000100/call
Sentiment Analysis
$0.000100/call
Intent Detection
$0.000080/call
Copywriting
$0.001050/call
Blog Writing
$0.004100/call
Marketing Copy
$0.001580/call
Product Descriptions
$0.000800/call
Related pages
Frequently asked questions
How much does Claude Haiku 5.5 cost for categorization per API call?
A typical categorization call using Claude Haiku 5.5 costs about $0.000155 per call. This estimate uses 800 input tokens and 150 output tokens at standard rates. Standard rates are $0.10 per million input tokens and $0.50 per million output tokens.
Is Claude Haiku 5.5 the best model for categorization?
Our benchmark data does not yet include a categorization ranking for Claude Haiku 5.5. We recommend testing it against your own evaluation criteria before production usage.
What is the cheapest model for categorization with good quality?
The most affordable model for categorization above 80/100 quality is GPT 5.6 Luna. It comes from GPT at $0.20 per million input tokens. Output costs $1.20 per million tokens with a quality score of 91/100. GPT 5.6 Luna costs more per call than Claude Haiku 5.5 but scores higher on quality benchmarks for this task type.
How can I reduce my Claude Haiku 5.5 costs for categorization?
Three strategies lower Claude Haiku 5.5 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 $0.000155 to about $0.000008 per call.
How does Claude Haiku 5.5 pricing compare to other Claude models?
Claude has 15 other models alongside Claude Haiku 5.5 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 Haiku 4.5 at $1.00/$5.00 per million tokens (fast / budget), 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). The right choice depends on whether your categorization workload prioritizes quality, cost, or speed.
What context window does Claude Haiku 5.5 support?
Claude Haiku 5.5 supports a context window of 1M tokens per API call. This sets the maximum combined length of your input prompt and generated response. For categorization, typical calls use 800 input and 150 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.