Free tool
LLM API Cost Calculator
Estimate your monthly OpenAI, Anthropic, and Google Gemini API spend. Compare the same workload across models and see what prompt caching would save. Prices from official provider pricing pages, verified 2026-05-20.
Same workload on other models
Your combined traffic priced on every model, cheapest first. This is the arithmetic behind model routing: many workloads run fine on a model several rows further down.
| Provider | Model | Monthly cost | vs your selection |
|---|
This math, live on your real traffic
SpendProxy sits in front of your AI APIs inside your own VPC, tracks every request at billing accuracy, and runs optimization engines — prompt cache injection, model routing, dedup, budget guardrails — on traffic you approve.
Current LLM API pricing reference
Per million tokens, from official provider pricing pages as of 2026-05-20. Cached input is the provider's cache-read rate (requires prompt caching to be set up correctly).
| Provider | Model | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
| OpenAI | gpt-5.5 | $5.00 | $0.500 | $30.00 |
| OpenAI | gpt-5.5-pro | $30.00 | — | $180.00 |
| OpenAI | gpt-5.4 | $2.50 | $0.250 | $15.00 |
| OpenAI | gpt-5.4-mini | $0.75 | $0.075 | $4.50 |
| OpenAI | gpt-5.4-nano | $0.20 | $0.020 | $1.25 |
| OpenAI | gpt-5.3-codex | $1.75 | $0.175 | $14.00 |
| OpenAI | gpt-4.1 | $2.00 | $0.500 | $8.00 |
| OpenAI | gpt-4.1-mini | $0.40 | $0.100 | $1.60 |
| OpenAI | gpt-4.1-nano | $0.10 | $0.025 | $0.40 |
| OpenAI | gpt-4o | $2.50 | $1.250 | $10.00 |
| OpenAI | gpt-4o-mini | $0.15 | $0.075 | $0.60 |
| OpenAI | o3 | $2.00 | $0.200 | $8.00 |
| OpenAI | o3-mini | $1.10 | $0.275 | $4.40 |
| OpenAI | o4-mini | $0.55 | $0.055 | $2.20 |
| Anthropic | claude-opus-4-7 | $5.00 | $0.500 | $25.00 |
| Anthropic | claude-sonnet-4-6 | $3.00 | $0.300 | $15.00 |
| Anthropic | claude-haiku-4-5 | $1.00 | $0.100 | $5.00 |
| Anthropic | claude-opus-4-1 | $15.00 | $1.500 | $75.00 |
| gemini-3.1-pro | $2.00 | $0.200 | $12.00 | |
| gemini-3.5-flash | $1.50 | $0.150 | $9.00 | |
| gemini-3.1-flash-lite | $0.25 | $0.025 | $1.50 | |
| gemini-2.5-pro | $1.25 | $0.125 | $10.00 | |
| gemini-2.5-flash | $0.30 | $0.030 | $2.50 | |
| gemini-2.5-flash-lite | $0.10 | $0.010 | $0.40 |
Notes: reasoning/thinking-token surcharges, batch discounts, long-context tier pricing, and cache-write fees are not modeled — actual bills vary with workload shape. Prices change; when they do, this page is updated from the same pricing database that powers SpendProxy's cost engine.