OpenAI Token Cost Calculator
Estimate OpenAI API spend from input and output tokens. Pick GPT-5, GPT-4.1, GPT-4o, or an o-series model, or enter custom $/1M rates. Cost = tokens ÷ 1,000,000 × price per 1M. Results are estimates; official OpenAI pricing prevails.
Math runs in your browser. Nothing is uploaded.
Custom $/1M rates (optional)
Estimated USD cost
—
Input cost
—
Output cost
—
Per 1k input tokens
—
Per 1k output tokens
—
Estimates only; official vendor pricing prevails (2026-10-30). Cost = tokens ÷ 1,000,000 × price per 1M.
Claude Token Cost Calculator · Gemini Token Cost Calculator · Grok Token Cost Calculator · LLM API Cost Calculator · RAG Cost Calculator
More in this group
- LLM Prompt Caching Cost Calculator No-cache vs cached prompt monthly cost and savings.
- OpenAI Flex vs Fast vs Standard Cost Calculator Standard vs Flex vs Fast monthly cost and deltas.
- OpenAI Web Search Cost Calculator Web search calls + content tokens vs model-only cost.
- DeepSeek Token Cost Calculator deepseek-flash / v4-pro cost, peak vs off-peak, cache hit/miss.
- Claude Token Cost Calculator Fable / Haiku / Sonnet / Opus token cost in USD.
- Gemini Token Cost Calculator Gemini 2.5 / 3 Flash and Pro token cost in USD.
- Grok Token Cost Calculator Grok 4.7 / 4.6 / 4.3 token cost in USD.
- Groq Token Cost Calculator Groq tokens + optional Whisper hours.
How it works
- How is OpenAI token cost calculated?
- USD cost = (input tokens ÷ 1,000,000 × input $/1M) + (output tokens ÷ 1,000,000 × output $/1M). With GPT-4o at $2.50 / $10 per 1M, 100,000 input + 20,000 output ≈ $0.45.
- What models are included?
- Presets cover GPT-6 Astra ($10 / $50), GPT-6.1 Sol ($2 / $10), GPT-6.1 Terra ($1 / $5), GPT-6 Luna ($0.10 / $0.50), plus GPT-5, GPT-5 mini, GPT-5 nano, GPT-4.1, GPT-4.1 mini, GPT-4o, GPT-4o mini, o3, and o4-mini at Standard list rates. Edit the $/1M fields for other snapshots or private rates.
- Does this include cached input or batch discounts?
- This page uses Standard input and output rates. GPT-6.1 Terra lists $1/$5 per 1M with cached input $0.05; prompts with more than 272K input tokens are priced at 2× input/cache and 1.5× output for the full request. Batch and Flex are 50% of Standard; Fast is 2×. Model caching with the prompt caching calculator; Batch with the Batch savings calculator; Flex/Fast with the Flex vs Fast vs Standard calculator.
- What is the GPT-6.1 Terra long-context rule?
- Official docs: prompts with more than 272K input tokens use 2× input and cache rates and 1.5× output for the entire request. Edit custom $/1M fields if you are modeling that band by hand.
- Is this the same as ChatGPT Plus?
- No. This page estimates API token spend. For Plus, Pro, or Go subscription totals use the ChatGPT Plus cost calculator.