Budget a chat completion
Plug in token counts before you ship a feature that calls GPT-5.6.
Sample
Input tokens: 3,200 Output tokens: 800
What you get
The tool multiplies by your selected per‑1M token rates so you can sanity‑check invoice size.
GPT Token & API Cost Calculator
Estimate your OpenAI API spend before you commit. This calculator loads current GPT models (including the GPT-5.6 Sol / Terra / Luna family) and per-1M token rates from OpenRouter — so when OpenAI ships a new model, it can appear here without a site rebuild. Enter input/output tokens and request volume for an instant cost breakdown. Live model lists and $/1M rates load from OpenRouter’s public models API (https://openrouter.ai/api/v1/models), with TensorFeed and a local snapshot as fallbacks. New releases (for example Gemini 3.8 Flash or Claude Fable 5.1) appear automatically when OpenRouter lists them.
GPT Token & API Cost Calculator
OpenAI · Local registry · as of 2026-09-02 · 3 models · refreshing…
Pricing data: OpenRouter models
Model Pricing (per 1M tokens)
| Model | Input | Output | Thinking |
|---|---|---|---|
| GPT-5.6 Sol | $2.00 | $10.00 | $10.00 |
| GPT-5.6 Terra | $2.00 | $12.00 | — |
| GPT-5.6 Luna | $0.20 | $1.20 | — |
Per Request
$0.007000
Daily
$0.7000
Monthly
$21.00
Annual
$252.00
How to Use This Tool
- Select the GPT model you plan to use (list refreshes from live OpenRouter pricing).
- Enter the estimated number of input tokens per request.
- Enter the estimated number of output tokens per request.
- Set the number of requests per day.
- View per-request, daily, monthly, and annual cost projections.
Features
- Live OpenAI models via OpenRouter
- Separate input and output token cost calculation
- Daily, monthly, and annual cost projections
- Side-by-side model pricing table
- Adapts when new GPT releases enter OpenRouter
Example
Frequently Asked Questions
How do you keep pricing current?
We proxy OpenRouter’s public /api/v1/models catalog (cached about 1 hour), then TensorFeed if needed. Rates and model names update when those feeds refresh. If both are down, we fall back to a local snapshot.
What if my invoice uses batch or cached rates?
This tool uses standard per-1M input/output list prices. Batch, flex, and cached-input discounts can be much lower — treat results as a planning baseline.
Will new GPT models show up here?
Yes — once they appear on OpenRouter under OpenAI, this calculator’s dropdown picks them up on the next refresh.
Related Tools
Claude API Cost Estimator
Estimate costs for Claude Fable 5.1 and other current Anthropic models with live pricing.
Gemini Token & API Cost Calculator
Calculate costs for Gemini 3.8 Flash and other current Google models with live pricing.
AI Token Counter & API Cost Calculator
Count tokens and estimate API costs across major LLMs — models update from OpenRouter live pricing.
Llama Self-Hosting Cost Estimator
Estimate GPU and cloud costs for self-hosting Llama models.
RAG vs Fine-Tuning Cost Comparison Calculator
Compare RAG and fine-tuning costs to find the optimal approach for your project.