GPT · Flagship · 128K context window
$0.008500 per call at 800 input / 150 output tokens.
Per call
$0.008500
10K calls/mo
$85
Cache savings
90% off input
Batch savings
50% off all
Adjust token counts, volume, and discount toggles to model your categorization spend. Pricing updated weekly.
Call GPT 5.5 with the OpenAI Python SDK:
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-5.5",
max_tokens=150,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.008500 per call at standard rates
# Input: $5.00/MTok
# Output: $30.00/MTokPer-call cost for all models scoring 50+ on categorization benchmarks. Hover for details.
Cheapest viable option: Gemini 3.5 Flash-Lite at $0.000425/call (95% less, 85/100 quality).
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $5.00 | 800 |
| Output | $30.00 | 150 |
Caching drops input cost from $5.00 to $0.50/MTok. For repeated system prompts, that saves $0.003600 per call.
Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.
| Monthly volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.008500 | $85 | $49 | $36 |
| 50,000 calls | $0.008500 | $425 | $245 | $180 |
| 100,000 calls | $0.008500 | $850 | $490 | $360 |
| 500,000 calls | $0.008500 | $4,250 | $2,450 | $1,800 |
| 1,000,000 calls | $0.008500 | $8,500 | $4,900 | $3,600 |
GPT 5.5 is a solid pick for categorization
Scores 85/100 (rank #3 of 14). Good balance of quality and cost for categorization.
Top-ranked: Gemini 3.5 Flash (92/100) at $0.002550/call
GPT 5.5 scores by task type. Categorization highlighted.
| Task type | Confidence score | Rank out of 14 |
|---|---|---|
| Reasoning | 95/100 | #2 |
| Code Generation | 91/100 | #3 |
| Creative Writing | 91/100 | #2 |
| Code Review | 90/100 | #3 |
| Q&A | 90/100 | #2 |
| Summarization | 89/100 | #3 |
| Extraction | 87/100 | #4 |
| Classification(current page) | 85/100 | #3 |
13 models score 80+ on categorization benchmarks, sorted by input rate. Cheapest: Gemini 3.5 Flash-Lite (95% less, 85/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs GPT |
|---|---|---|---|---|---|---|
| Gemini 3.5 Flash-Lite | Gemini | $0.25 | $1.50 | 85/100 | $0.000425 | 95% cheaper |
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 88/100 | $0.000850 | 90% cheaper |
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 90/100 | $0.001550 | 82% cheaper |
| GPT 5.6 Luna | GPT | $1.00 | $6.00 | 91/100 | $0.001700 | 80% cheaper |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 92/100 | $0.002550 | 70% cheaper |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 86/100 | $0.003100 | 64% cheaper |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 86/100 | $0.003400 | 60% cheaper |
| GPT 5.4 | GPT | $2.50 | $15.00 | 88/100 | $0.004250 | 50% cheaper |
| GPT 5.6 Terra | GPT | $2.50 | $15.00 | 89/100 | $0.004250 | 50% cheaper |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 84/100 | $0.004650 | 45% cheaper |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 80/100 | $0.007750 | 9% cheaper |
| GPT 5.6 Sol | GPT | $5.00 | $30.00 | 86/100 | $0.008500 | same cost |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 82/100 | $0.0155 | 82% more |
Provider
GPT
Tier
Flagship
Context
128K tokens
Released
Mar 2026
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| GPT 5.4 | Mid-tier | $2.50 | $15.00 | 128K |
| GPT 5.6 Sol | Flagship | $5.00 | $30.00 | 1,000K |
| GPT 5.6 Terra | Mid-tier | $2.50 | $15.00 | 1,000K |
| GPT 5.6 Luna | Fast / Budget | $1.00 | $6.00 | 1,000K |
You can compare GPT 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.
See how GPT 5.5 costs change across different workload types.
Code Generation
$0.1300/call
Unit Test Generation
$0.1650/call
SQL Generation
$0.0375/call
API Generation
$0.1950/call
Code Refactoring
$0.1400/call
Code Review
$0.0850/call
PR Review
$0.1300/call
Security Review
$0.1050/call
Bug Detection
$0.0850/call
Document Summarization
$0.0800/call
PDF Summarization
$0.1200/call
Meeting Notes
$0.1000/call
Email Summarization
$0.0300/call
Chatbot
$0.0400/call
RAG Pipeline
$0.0750/call
Customer Support Bot
$0.0450/call
FAQ Bot
$0.0315/call
Data Extraction
$0.0500/call
JSON Extraction
$0.0390/call
Invoice Parsing
$0.0280/call
Resume Parsing
$0.0365/call
Chain of Thought
$0.1650/call
Legal Analysis
$0.1700/call
Math Reasoning
$0.0975/call
Financial Analysis
$0.1600/call
Content Moderation
$0.005500/call
Sentiment Analysis
$0.005500/call
Intent Detection
$0.004500/call
Copywriting
$0.0625/call
Blog Writing
$0.2450/call
Marketing Copy
$0.0940/call
Product Descriptions
$0.0475/call
$0.008500 per call at 800 input / 150 output tokens.
Scores 85/100, rank #3 of 14 models. Top-ranked: Gemini 3.5 Flash at 92/100.
Gemini 3.5 Flash-Lite scores 85/100 quality at $0.25/$1.50 per MTok. That is 95% less than GPT 5.5 per call.
Three strategies: prompt caching (90% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.008500 drops to about $0.000425 per call.
GPT also offers: GPT 5.4 at $2.50/$15.00, GPT 5.6 Sol at $5.00/$30.00, GPT 5.6 Terra at $2.50/$15.00, GPT 5.6 Luna at $1.00/$6.00.
128K tokens total. Typical categorization calls use 800 plus 150 tokens, well within limits.
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.