LLM API Cost Calculator
How much will your LLM API bill actually be? Enter your average input and output tokens per request plus your monthly request volume, and this calculator estimates your monthly spend across 7 leading models — GPT-6.1 Sol, GPT-6 Astra, Claude Sonnet 5.5, Claude Opus 5.5, Gemini 3.8 Flash, Grok 4.7 and DeepSeek V4.1 Flash — using verified October 2026 pricing.
Prices verified as of 2026-10-02 from press reporting of official pricing pages
| Model | Input $/1M | Output $/1M | Per request | Per month |
|---|
Cheapest option for your inputs is highlighted. Costs = (input tokens ÷ 1M × input price + output tokens ÷ 1M × output price) × requests. Estimates exclude caching discounts, batch APIs, and taxes.
Current LLM API prices (per 1M tokens)
| Model | Provider | Input | Output | Notes |
|---|---|---|---|---|
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | Announced DevDay, Sep 29 2026 |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | Flagship tier |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | Released Sep 28 2026 |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | Flagship tier |
| Gemini 3.8 Flash | $0.75 | $3.75 | Intro price through Dec 31, 2026; $1.50/$7.50 after | |
| Grok 4.7 | xAI | $2.00 | $6.00 | Prompts up to 200K tokens |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | Peak hours; off-peak $0.15/$0.60 |
All prices reported October 2026 — verify on the providers' official pricing pages before budgeting, as prices change frequently. Official pages: openai.com/api/pricing · anthropic.com/pricing · ai.google.dev/gemini-api/docs/pricing · platform.deepseek.com. This page is refreshed quarterly; cached-input, batch, and tiered rates are not modeled.
Frequently Asked Questions
How is LLM API cost calculated?
Providers charge separately for input tokens (what you send) and output tokens (what the model generates). Monthly cost = (input tokens per request ÷ 1,000,000 × input price + output tokens per request ÷ 1,000,000 × output price) × requests per month. This calculator applies that formula to each model's verified per-million-token rates.
Which LLM API is cheapest in 2026?
At verified October 2026 prices, DeepSeek V4.1 Flash is the cost floor ($0.30 input / $1.20 output per million tokens at peak hours, half that off-peak), followed by Gemini 3.8 Flash at $0.75/$3.75 through December 2026. The cheapest model for your workload depends on your input/output mix — enter your numbers above to see the ranking for your case.
Why do LLM API prices change so often?
Model providers cut prices as hardware gets cheaper and competition intensifies — 2026 alone saw cuts from OpenAI (GPT-6.1 Sol at DevDay), Google (three Flash generations at promotional rates), and DeepSeek. Always check the provider's official pricing page before budgeting; this page's prices were verified 2026-10-02 and are refreshed quarterly.
What about cached input and batch discounts?
Most providers discount repeated context: e.g. GPT-6.1 Sol cached input is $0.10/M vs $2.00/M standard, and batch APIs typically halve list prices. This calculator uses standard rates only, so heavy caching or batch usage will come in cheaper than shown.
Are these prices current?
Prices were verified as of 2026-10-02 from reporting on the providers' official pricing pages. LLM pricing moves fast — treat these as planning estimates and confirm on openai.com/api/pricing, anthropic.com/pricing, ai.google.dev/gemini-api/docs/pricing, or platform.deepseek.com before signing a budget.
Is my usage data private?
Yes. The calculator runs 100% in your browser — your token counts and estimates never leave your device.