Nythrex

Free tool · Running costs

What will your AI feature cost per month?

Enter your traffic and prompt sizes, pick a model tier or type your provider’s current prices, and see the monthly bill — before the invoice tells you.

LLM API cost calculator

System prompt + retrieved context + user message

Example price tiers — replace them with your provider’s current price list.

Cached input is typically billed at a fraction of the normal price; we assume 10%.

Estimated monthly cost

$251

/ month

Per request

$0.0042

Per 1,000 requests

$4.19

Same traffic on each example tier

Small / fast model
$34
Mid-tier model
$251
Frontier model
$1,257

Biggest levers: shorter system prompts, fewer retrieved chunks, caching, and routing easy requests to a smaller model.

Already live and the bill keeps growing? We review prompts, retrieval and model routing and tell you where the money goes.

Get a cost review

How to fill it in realistically

  1. 1

    Input tokens are bigger than you think

    Count the system prompt, the conversation history and every retrieved passage — not just the user’s question. In RAG systems, retrieved context often dominates.

  2. 2

    Output tokens cost more

    Most providers charge several times more for output than input. Long answers and verbose reasoning add up.

  3. 3

    Multiply by calls per request

    Agents and multi-step pipelines make several model calls per user request. Enter the total tokens across all calls.

  4. 4

    Use your provider’s current price list

    Prices change often and differ by model and region. The tiers here are examples, not quotes.

Frequently asked questions

Keep reading

Guide11 ways to cut your LLM billLLM cost optimisation: prompt caching, model routing, shorter context, better retrieval, batching and budgets — checked against evals so quality holds.GuideWhat AI development really costsWhat drives AI project cost — the model is the cheap part. Effort by phase, hidden costs vendors skip, running costs and how to budget safely.Free toolAI project effort estimatorFree AI project calculator: six questions → timeline, team, effort in person-weeks and the main cost drivers of your AI project. No signup.ComparisonOpenAI vs Azure OpenAI vs AnthropicChoosing an LLM platform: OpenAI, Azure OpenAI, Anthropic (direct, Bedrock, Vertex AI), Gemini and open-weight — by data, procurement and quality.Free toolAI automation ROI calculatorCalculate hours freed, net monthly saving and payback period for an AI automation — using your own task volumes, costs and a conservative automation share.

Want a second opinion on your project?

Tell us what you’re building and where you’re stuck. We’ll reply within one business day with the most practical next step — even if that step isn’t us.

Start a project