Free Tool
LLM API Pricing Calculator
Enter your token volumes and request counts to instantly compare estimated API costs across OpenAI, Anthropic, and Google models side by side. 100% private - everything runs in your browser.
100% in your browser - no signup, no uploads.
Comparing 9 models at 1,000 input + 500 output tokens per request, 10,000 requests per month.
| Model | Input $/1M | Output $/1M | Cost / request | Cost / day | Cost / month |
|---|---|---|---|---|---|
GPT-4o miniCheapest OpenAI | $0.15 | $0.60 | $0.0004 | $0.15 | $4.50 |
Gemini 2.5 Flash Google | $0.30 | $2.50 | $0.0015 | $0.52 | $15.50 |
Claude Haiku 4.5 Anthropic | $1.00 | $5.00 | $0.0035 | $1.17 | $35.00 |
GPT-4.1 OpenAI | $2.00 | $8.00 | $0.0060 | $2.00 | $60.00 |
Gemini 2.5 Pro Google | $1.25 | $10.00 | $0.0063 | $2.08 | $62.50 |
GPT-4o OpenAI | $2.50 | $10.00 | $0.0075 | $2.50 | $75.00 |
Claude Sonnet 4.6 Anthropic | $3.00 | $15.00 | $0.01 | $3.50 | $105.00 |
Claude Opus 4.8 Anthropic | $5.00 | $25.00 | $0.02 | $5.83 | $175.00 |
Claude Fable 5 Anthropic | $10.00 | $50.00 | $0.04 | $11.67 | $350.00 |
Tip: prompt caching can cut input costs
Anthropic prompt caching can reduce the cost of cached input tokens to roughly 0.1x the standard rate, which is a major saving when you reuse the same system prompt or context across many requests. The numbers above use standard, uncached pricing.
Pricing as of June 2026. Verify current rates with each provider.
How to estimate your LLM API costs
This LLM pricing calculator is a free AI API cost calculator that lets you compare OpenAI, Anthropic, and Google models side by side. Large language model providers bill per token, and they charge different rates for input tokens (your prompt and context) and output tokens (the generated response). Because output is usually priced three to five times higher than input, the real driver of your bill is how much text each request generates, not just how many requests you send.
To use the OpenAI API cost calculator and Claude API pricing comparison above, enter a realistic estimate of input and output tokens for a typical request, then set your request volume per day or per month. The tool computes cost per request as (input tokens / 1,000,000 x input price) + (output tokens / 1,000,000 x output price), then scales that to daily and monthly totals using a 30-day month. The cheapest model by monthly spend is highlighted automatically, so you can see at a glance whether GPT-4o mini, Gemini 2.5 Flash, or Claude Haiku 4.5 wins for your workload.
For a quick LLM cost comparison: lightweight models like GPT-4o mini and Gemini 2.5 Flash are the cheapest options for high-volume, simple tasks such as classification, extraction, and short replies. Mid-tier models like Claude Sonnet 4.6, GPT-4.1, and Gemini 2.5 Pro balance quality and AI API pricing for agents and retrieval workloads. Premium models like Claude Opus 4.8 and Claude Fable 5 cost more per token but can reduce overall spend on hard tasks by getting the answer right the first time and needing fewer retries.
Remember that this GPT API cost calculator shows standard, uncached rates. In production you can lower real costs with prompt caching, batch processing, shorter system prompts, and capping max output tokens. GPT-4o pricing, Claude pricing, and Gemini pricing all change over time, so always confirm the current published rates on each provider's official pricing page before you commit a model to production.
Working out token counts before you estimate cost? Pair this calculator with our LLM Token Counter to measure exactly how many tokens your prompts use across GPT, Claude, and Gemini.
FAQ
Frequently asked questions
Newsletter
Get the best new AI tools weekly.
One short email a week: new tools worth trying, honest verdicts, and practical picks from the ToolJunction team.
LLM cost tools
Estimate the real cost before you ship
Move from prompt length to model pricing without leaving your browser.
Explore the catalog
AI tool categories
Discover and compare the best AI tools, ranked and reviewed.