AI & ML APIs – Public APIs Directory

About AI & ML APIs

Model inference and AI services with per‑minute or token‑based rate limits.

Row Types:

Special Indicators:

Use the toolbar's Info button to toggle this panel.
Use Tags toggle to enable/disable row color-coding.
Use Sub-tags toggle to show/hide special indicators.
Return to ← Home to explore all categories.

Favorites

No favorites yet. Tap ☆ on any game.

AI & ML APIs

OpenAI — Token‑based limits per org/model
Anthropic — Throughput & RPM limits
Google AI Studio / Vertex AI — Quota & rate configs per model
Cohere — RPM & TPM per plan
Hugging Face Inference — Hosted models; quotas
Replicate — Per‑call pricing & limits
AssemblyAI — Speech APIs; usage limits
ElevenLabs — TTS quotas per plan
Stability AI — Image APIs; rate limits
OpenRouter — Federated LLM gateway with quotas