Live AI API Pricing & Cloud GPU Break-Even Calculator

Compare live per-token pricing across 468 AI models from OpenAI, Anthropic, Google, DeepSeek, Mistral, Qwen, Meta, and xAI — calculate real monthly spend with prompt caching, or check when self-hosting on a Cloud GPU beats API costs.

Live Models Tracked
468
Auto-synced every 12h
Providers Indexed
67
Unified pricing schema
Prompt-Cache Models
340
354 reasoning models
Free API Tiers
14
$0.00 / 1M tokens

1. Live Monthly LLM Cost & Prompt Caching Calculator

Loading models...
Model ⇅ Capabilities Context ⇅ In / 1M ⇅ Out / 1M ⇅ Est. / Mo (Cached) ⇅ Est. / Mo (Raw)

2. Self-Host Cloud GPU vs. API Break-Even Calculator

Calculating...
Est. GPU Cost
—

Recommended Cloud GPUs & Unified API Routers

Best for H100 / A100 / 4090

RunPod Cloud GPUs

Spin up on-demand H100, A100, and RTX 4090 pods or serverless vLLM endpoints in seconds.

Launch GPU on RunPod →
Predictable Cloud Infra

DigitalOcean GPU Droplets

Deploy AI inference APIs, vector databases, and GPU droplets with simple monthly billing.

Try DigitalOcean →
Global Low-Latency Regions

Vultr Cloud GPU

Run dedicated NVIDIA H100/A100/L40S instances across 32 global data center regions.

Deploy on Vultr →
1 API Key · 470+ Models

OpenRouter Unified API

Switch between Gemini, Claude, GPT, DeepSeek, and Llama with one OpenAI-compatible key.

Get Unified API Key →

Newest AI Models Added

Popular Head-to-Head Model Pricing Comparisons

Browse Pricing by AI Lab / Provider