Free tool · Runs in your browser
LLM API Cost Calculator
Enter tokens per request and requests per month to compare the monthly API bill across Claude, GPT and Gemini models, in USD, CAD or AUD.
Your inputs stay in your browser and in the share link. Nothing is sent to a server.
How it works
Each model's monthly cost is requests × cost per request. The cost per request is:
(input × (1 − cached share) × input price + input × cached share × cache-read price + output × output price) ÷ 1,000,000
- Batch: uses each vendor's listed Batch prices (half of Standard on every model here). Batch is asynchronous and not for live chat.
- Announced increases: swaps in the higher prices Google has published for Gemini 4 Argon (from 1 Dec 2026) and Gemini 3.8 Flash (from 1 Jan 2027).
- Not included: cache-write fees, reasoning or thinking overhead you can't predict, tool and search fees, long-prompt surcharges, regional or fast-mode uplifts, taxes and volume discounts.
Prices used (USD per 1M tokens, Standard, checked 2026-10-31)
| Model | Input | Output | Cache read | Batch in / out |
|---|---|---|---|---|
| Anthropic Claude Fable 5.1 | $10.00 | $50.00 | $0.2500 | $5.00 / $25.00 |
| Anthropic Claude Opus 5.5 | $4.00 | $20.00 | $0.2000 | $2.00 / $10.00 |
| Anthropic Claude Sonnet 5.5 | $2.00 | $10.00 | $0.1000 | $1.00 / $5.00 |
| Anthropic Claude Haiku 5.5 (prompts up to 100k) | $0.1000 | $0.5000 | $0.0100 | $0.0500 / $0.2500 |
| OpenAI GPT-6 Astra | $10.00 | $50.00 | $1.00 | $5.00 / $25.00 |
| OpenAI GPT-6.1 Sol | $2.00 | $10.00 | $0.1000 | $1.00 / $5.00 |
| OpenAI GPT-6.1 Terra | $1.00 | $5.00 | $0.0500 | $0.5000 / $2.50 |
| OpenAI GPT-6 Luna | $0.1000 | $0.5000 | $0.0100 | $0.0500 / $0.2500 |
| Google Gemini 4 Argon | $2.00 | $10.00 | $0.1000 | $1.00 / $5.00 |
| Google Gemini 3.8 Flash | $0.7500 | $3.75 | $0.0750 | $0.3750 / $1.88 |
| Google Gemini 3.5 Flash-Lite | $0.3000 | $2.50 | $0.0300 | $0.1500 / $1.25 |
| Google Gemini 3.1 Pro Preview (prompts up to 200k) | $2.00 | $12.00 | $0.2000 | $1.00 / $6.00 |
Announced steps: Gemini 4 Argon moves to $4.00 input and $20.00 output from 1 Dec 2026; Gemini 3.8 Flash moves to $1.50 and $7.50 from 1 Jan 2027. Both are listed on Google's page. OpenAI's page also mentions promotional pricing on one model through 21 Nov 2026 without tying it to a table row, so we use the table prices as shown.
Sources, all read on 2026-10-31: Anthropic pricing, OpenAI API pricing, Gemini API pricing. FX: Bank of Canada (1.3960 CAD per USD) and Reserve Bank of Australia (0.7040 USD per AUD), 30 Oct 2026.
Educational estimate, not financial advice. Vendors change prices often; confirm on their pages before you commit.
Related guides
Worked example
A support bot sends 2,000 input tokens and gets 500 output tokens back, 100,000 times a month, with no caching. On Standard prices that is $45 a month on Claude Haiku 5.5 or GPT-6 Luna, $450 on GPT-6.1 Terra, $900 on Claude Sonnet 5.5, GPT-6.1 Sol or Gemini 4 Argon, and $4,500 on Claude Fable 5.1 or GPT-6 Astra. Switch to the after-increases prices and Gemini 4 Argon doubles to $1,800 while Gemini 3.8 Flash goes from $337.50 to $675. In CAD at 1.3960, the $900 models cost about C$1,256.
Frequently asked questions
How does the LLM API cost calculator work out the monthly cost?
Which models and prices does it use?
What do the cached share and Batch options change?
Why does "after announced increases" change two Google models?
Where do the CAD and AUD figures come from?
Do Anthropic, OpenAI and Google count tokens the same way?
Newsletter
Get new tools by email
New free calculators for founders, plus the AI and startup guides behind them. Free, unsubscribe anytime.