trelvane
100% Free Forever 100% Private · Inputs Never Saved No Sign-Up Required

OpenAI GPT-5, GPT-4o & o3-mini API Cost Calculator

Count exact BPE subword tokens and calculate per-request, per-1,000 calls, and monthly production API costs across OpenAI GPT-5 ($2/$8), GPT-4o ($2.50/$10), GPT-4o mini ($0.15/$0.60), and o3-mini.

Live BPE: 125 tokens · 47 words · 354 chars (2.83 chars/tok)
Override Input Tokens:
Quick Sample Scenario:
Calculating...
Monthly Production API Bill (120,000 Calls/Mo)
$1,248.00/ mo$0.01040 / call · $10.40 / 1K calls
Tokens/Call: 2,000 in + 800 outContext Used: 0.28% of 1000K
All 11 Frontier Models Side-by-Side (120,000 Calls/Mo)
ModelPer 1K CallsMonthly Bill
Claude 4 Sonnet($3/$15)$18.00$2,160.00
GPT-5 / 4.1($2/$8)$10.40$1,248.00
GPT-4o($2.5/$10)$13.00$1,560.00
GPT-4o mini($0.15/$0.6)$0.78$93.60
OpenAI o3-mini($1.1/$4.4)$5.72$686.40
Claude 4 Opus($15/$75)$90.00$10,800.00
Claude 3.5 Haiku($0.8/$4)$4.80$576.00
Gemini 2.5 Pro($1.25/$10)$10.50$1,260.00
Gemini 2.5 Flash($0.15/$0.6)$0.78$93.60
DeepSeek R1($0.27/$1.1)$1.42$170.40
Llama 4 70B($0.59/$0.79)$1.81$217.44
Caching 75% of repeated system prompts saves $270.00/mo!

11-Model API Cost Comparison (2,000 Input + 800 Output Tokens)

Model Cost / 1K Calls Monthly Bill (120,000 Calls)
Anthropic Claude 4 Sonnet / 3.7 Sonnet $18.00 $2,160.00 / mo
OpenAI GPT-5 / GPT-4.1 Flagship $10.40 $1,248.00 / mo
OpenAI GPT-4o Multimodal $13.00 $1,560.00 / mo
OpenAI GPT-4o mini (High-Speed) $0.78 $93.60 / mo
OpenAI o3-mini / o4-mini (Reasoning) $5.72 $686.40 / mo
Anthropic Claude 4 Opus $90.00 $10,800.00 / mo
Anthropic Claude 3.5 Haiku $4.80 $576.00 / mo
Google Gemini 2.5 Pro (2M Context) $10.50 $1,260.00 / mo
Google Gemini 2.5 Flash (1M Context) $0.78 $93.60 / mo
DeepSeek R1 / V3 Reasoning API $1.42 $170.40 / mo
Meta Llama 4 70B / 405B (Groq / Together) $1.81 $217.44 / mo

Frequently Asked Questions

How does OpenAI Prompt Caching reduce GPT-5 and GPT-4o input token costs? ▾

OpenAI automatically caches repeated prompt prefixes longer than 1,024 tokens (such as system instructions, few-shot examples, and tool definitions), discounting cached input tokens by 50% to 75%.

Are reasoning tokens in o3-mini and o4-mini billed as input or output tokens? ▾

OpenAI bills internal chain-of-thought reasoning tokens at the model’s output token rate ($4.40 per 1M tokens on o3-mini), even though they are hidden from the final API text response.