Built for developers who need to pick the right LLM, fast.
Our Mission
AI API Cost launched in 2026 as a side project to solve a simple problem: "Which AI model gives me the best performance per dollar, right now.
With 500+ models across 20+ providers, pricing changes daily. We aggregate real API data, so you don't have to.
What We Track
- Real-time pricing from OpenRouter and other public APIs
- Live benchmark scores (Intelligence Index, GPQA, MATH, HumanEval
- Feature matrices for vision, tool use, JSON mode, reasoning, context windows
- Speed measurements (tokens/sec, time-to-first-token)
- Subscription plan comparisons for coding assistants
- Real-world agent performance (PinchBench)
Data Sources
All data comes from public, verifiable sources:
- OpenRouter — pricing and model metadata
- Anthropic Arena — benchmark leaderboard scores
- Provider public APIs — official pricing and features
- PinchBench — real-world agent task scores
We don't make up numbers. Every datapoint is sourced.
Who Built This
AI API Cost is built and maintained by a small team of developers building AI-powered tools. We use this site ourselves every day for our own projects, and we decided to make it public because it was too useful to keep private.
Open Source
The site is fully open source. You can find the code on GitHub. Contributions are welcome.
Editorial Standards
Every datapoint on this site is sourced to a public, verifiable source. We do not publish made-up numbers, sponsored placements, or “sponsored bias” in benchmark rankings.
- Sourcing. Each model card, comparison, and benchmark chart links back to its data origin (OpenRouter, the provider's pricing page, or Artificial Analysis for cross-vendor benchmarks).
- Freshness. Pricing is re-fetched hourly from upstream APIs; benchmark scores are refreshed when Artificial Analysis publishes updates. The “Last refreshed” timestamp on each page documents when the source was last verified.
- Corrections. If you spot an error (wrong price, stale benchmark, dead comparison page), email us and we will investigate and fix within 48 hours. Corrections are documented in the GitHub commit history.
- Editorial independence. Affiliate and sponsor placements are kept clearly separate from raw data tables and benchmark rankings. Sponsors never see ranking numbers before the public does.
- AI-assisted prose. The site uses data-driven narrative sections to summarise model positioning. Each summary is generated from the same public data you see above — never from vibes or speculation. We do not publish AI-text without underlying data.
Methodology
For benchmarks we rely on Artificial Analysis as the primary cross-vendor source. Their methodology scores each model on the same set of tests (Intelligence Index, Coding Index, Math Index, GPQA Diamond, AIME, MATH-500, HumanEval variants, etc.) so numbers are comparable across providers.
For pricing we use OpenRouter's public listing as the authoritative cross-vendor source, with provider-direct pages as fallback when OpenRouter does not carry the model.
For speed we use Artificial Analysis' median tok/s and TTFT measurements, taken on standard hardware and reported per-model.
Contact
Questions, feedback, bug reports, feature requests:
hello@aiapicost.com
← Back to AI API Cost