LLM API Cost Calculator
Compare AI API prices and estimate monthly GPT, Claude and Gemini token costs.
Prices last updated: November 18, 2026. USD per 1 million tokens; verify linked provider rates before budgeting.
Monthly usage estimate
Formula: monthly cost = (input tokens × input rate + output tokens × output rate) ÷ 1,000,000 × requests.
| Provider / model | Input / 1M | Output / 1M | Estimated monthly cost |
|---|---|---|---|
| OpenAI · GPT-6.1 Terra | $0.50 | $2.50 | $1.13 |
| Anthropic · Claude Sonnet 5.5 | $2.00 | $10.00 | $4.50 |
| Google · Gemini 3.1 Pro Preview | $2.00 | $12.00 | $5.00 |
How to use this LLM cost calculator
- Enter average input and output tokens used by one request.
- Enter expected requests for a month.
- Compare monthly estimates; use provider links to verify exact model and tier pricing.
Formula and worked example
Cost = input tokens ÷ 1,000,000 × input price + output tokens ÷ 1,000,000 × output price. Monthly estimate multiplies that per-request cost by requests.
Example: 1,000,000 input + 250,000 output tokens per request, once monthly, on GPT-6.1 Terra: (1 × $0.50) + (0.25 × $2.50) = $1.125, about $1.13.
Frequently asked questions
Are these all API costs?
No. Tool calls, image or audio processing, caching, batch tiers, taxes, and provider-specific billing can add or change charges.
How often do prices change?
Providers can change prices at any time. We review this static dataset monthly; check the linked official pages before making a budget decision.
How do I estimate tokens?
Use the AI Token Counter to estimate prompt tokens.
Estimates are arithmetic comparisons, not a quote. Price data is static and may be out of date. Related: AI Token Counter · LLM VRAM Calculator.
See also
- Not sure how many tokens your prompt uses? Use the AI tokens calculator.
- Prefer to run it locally? Check the memory you need with the LLM RAM calculator.
Related Tools
- RAG Chunking and Embedding Cost CalculatorEstimate RAG chunk count, one-off embedding (indexing) cost and monthly query cost from document size, chunk size, overlap, embedding price and retrieval settings. Prices are dated and editable.
- AI Token CounterCount tokens, words and characters in your prompts for GPT, Claude, Gemini and Llama.
- Tokens to Words, Pages and Books ConverterHow many tokens in a word, page or 1,000 words? Convert words, pages and books to tokens and back for six languages.
- LLM VRAM CalculatorEstimate how much GPU memory (VRAM) you need to run a local LLM, and which GPUs can run it.
- KV Cache CalculatorMemory per token and total KV cache from layers, KV heads, head dimension, context, batch and precision, with GQA and context-length views.
- LLM Tokens per Second CalculatorEstimate local LLM generation speed from GPU memory bandwidth, model size and quantization.