Estimate LLM API costs for your team

We estimate daily token usage based on your team size, chats per user, response length, and image/PDF uploads. Tokens are split 40% input / 60% output to reflect typical conversations. The token count is then multiplied by each model's per-million-token price. When multiple models are selected, usage is distributed evenly across them.

LLM providers charge separately for input tokens (your prompts, uploaded documents, images) and output tokens (the model's responses). Output tokens are typically more expensive because they require more compute to generate.

It adds the model to your cost estimate. When you select multiple models, the tool assumes your team's usage is split evenly across them — so each model handles a proportional share of chats, images, and documents. The total is the sum of all models' shares.

Yes. Use the provider tabs to filter by vendor, or search for specific models. Add multiple models to see a side-by-side cost breakdown in the left panel. You can also sort by price to quickly find the cheapest or most expensive options.

It ranks models by a composite score that factors in feature support (attachments, reasoning, tool calling, temperature control), the number of input/output modalities, how recently the model was released or updated, and whether it comes from a major provider.

The context window is the maximum number of tokens a model can process in a single request — including both your input and the model's output. Larger context windows let you send longer documents or maintain longer conversation histories, but may cost more.

This tool provides a ballpark estimate. Actual costs may differ due to prompt caching, batched API calls, volume discounts, reasoning token overhead, and provider-specific billing rules. Use it for budgeting and comparison, not as an invoice prediction.