Free LLM Token Cost Calculator

Calculate your true LLM token costs

See exactly what GPT-4o, Claude, Gemini, and 200+ models cost at official rates, then how much less you'd pay routing each request through doteb's cheapest provider.

200+ modelsZero platform markupFree, no signup
1
GPT-4o Mini

Official (OpenAI)

$0.15/M in · $0.60/M out

doteb (OpenAI)

$0.15/M in · $0.60/M out

Official price

$0.2100

direct from providers

doteb

$0.2100

cheapest provider per model, no markup

You save

$0.00

same price, more features

Share these results

Send this breakdown to your team or post it in one click.

modelTokensOfficialdotebSaved

GPT-4o Mini

via OpenAI

1.0M in
100K out
$0.2100$0.2100
Total$0.2100$0.2100

Smart Routing

Automatically routes to the cheapest available provider for each model

No Markup

Zero platform fees - you pay exactly what the provider charges

Automatic Failover

If one provider is down, requests automatically route to the next cheapest

Processing high volume?

Enterprise plans include volume discounts, dedicated support, custom SLAs, and extended data retention.

Talk to Sales

Ready to cut your LLM costs?

Start for free with no platform fees. No credit card required.

How the LLM cost calculator works

Estimate your monthly spend across any model in three steps, then see how much routing through doteb saves you.

  1. Step 1

    Add the models you use

    Pick from 200+ LLMs across OpenAI, Anthropic, Google, Mistral, Meta, and more. Stack as many models as you want to compare side by side.

  2. Step 2

    Enter your token volumes

    Set the input and output tokens you expect to process, or start from a Light, Medium, Heavy, or Intensive preset and adjust from there.

  3. Step 3

    Compare and start saving

    Instantly see official provider pricing next to doteb's cheapest routed provider, plus the exact amount you would save each cycle.

Understanding LLM token costs

Every large language model bills by the token, the small chunks of text a model reads and writes. Roughly speaking, one token is about four characters of English, so 1,000 tokens is around 750 words. Providers quote prices per million tokens, and they charge separately for the tokens you send (input) and the tokens the model generates (output).

Output tokens are usually two to four times more expensive than input tokens, so the ratio between your prompt size and response size has a big impact on your bill. A summarization workload that reads a lot and writes a little costs very differently from a code-generation workload that writes long responses. The calculator above keeps the two separate so your estimate reflects how you actually use each model.

Prices also vary by provider. A single popular model is often hosted by several providers at different rates, and those rates change as providers compete on price. Instead of locking yourself into one provider, doteb routes each request to the cheapest available provider for that model through one OpenAI-compatible API, with no platform markup. That is the gap the calculator shows: the official list price versus the lowest live price you would actually pay.

Use it to budget a new feature, compare GPT-4o against Claude or Gemini before you commit, or build the business case for switching providers. When the numbers look good, you can start for free and keep the same estimate in production.

Frequently asked questions

Everything you need to know about estimating and lowering your LLM token costs.

What are input tokens and output tokens?

Input tokens are everything you send to the model, including your prompt, system message, and conversation history. Output tokens are what the model generates back. Output tokens almost always cost more than input tokens, which is why the split matters when you estimate spend.

Why can the same model have different prices?

Popular models are often served by several providers at different rates, and prices change as providers compete. doteb routes each request to the cheapest available provider for that model, so you pay the lowest live rate without changing any code.

Does doteb add a platform markup?

No. doteb shows provider pricing without a platform markup. You pay for model usage and can route to the cheapest provider available for each request.

How do I lower LLM API costs?

Route through a gateway that compares providers and picks the lowest price per request. Because doteb supports 200+ models behind one OpenAI-compatible API, you can switch models or providers based on cost without rewriting your integration.