Every model, one table.

Per-token prices verified against official pricing pages — plus what they mean per month for a typical workload. Click a column to sort.

Tier Provider
Model $ input /1M $ output /1M $ cached /1M Batch Context ≈ $/mo *

* Example workload — chatbot, 100k requests/mo, 2,000 input / 300 output tokens per request, 70% of input cached. Computed by the same engine as the calculator; price it at your own volume there. Cached = price per 1M cached input tokens where the provider publishes one. Tiers are our editorial grouping — model classes change, we re-sort on every pricing revision.

These numbers at your volume
Pick a use case, set your requests — the calculator prices all 18 models with your token mix and cache share.
Open calculator
OpenAI pricing → Anthropic pricing → Gemini pricing → DeepSeek pricing → Grok pricing → Mistral pricing → Price changelog →