Chatbot
1,000 in / 500 out
Use this as a first pass for short customer support, FAQ, or in-app assistant messages.
Open Chatbot guideCalculator guide
LLM API cost calculator examples for four common workloads
Token calculators are easiest to trust when the inputs start from a real workload shape. This guide explains the four presets already available on the calculator, then routes each one to a guided use-case page where the same cost idea is easier to inspect.
Preset map
Start with the preset that matches the product behavior
Presets are input helpers, not model recommendations. Change the token counts and monthly request volume before making a production decision.
| Workload | Input tokens | Output tokens | Monthly requests | Best next page |
|---|---|---|---|---|
| Chatbot chatbot preset | 1,000 | 500 | 10,000 | Open guide |
| RAG answer RAG answer preset | 4,000 | 800 | 5,000 | Open guide |
| Summarization summarization preset | 20,000 | 1,000 | 1,000 | Open guide |
| Coding agent coding-agent preset | 8,000 | 4,000 | 2,000 | Open guide |
RAG answer
4,000 in / 800 out
Use this when each answer includes retrieved text and the input side drives most of the cost.
Open RAG answer guideSummarization
20,000 in / 1,000 out
Use this for long documents, reports, transcripts, or article batches where input tokens dominate.
Open Summarization guideCoding agent
8,000 in / 4,000 out
Use this for repeated agent turns where repository context and generated code both matter.
Open Coding agent guideUse the calculator, then inspect candidate models
The calculator gives a monthly estimate for one selected model. The use-case pages and compare tool help you check whether cheaper nearby routes also fit the workload.
Caveats
What these examples do not decide
These examples do not rank model quality, latency, rate limits, cache behavior, discounts, or provider-specific add-on charges. They are starting shapes for monthly API cost estimation. Use the calculator for your own token counts, then confirm final pricing with the provider before production use.