Data Sources

Every provider pricing page and API documentation source we monitor. Prices are verified manually against these pages weekly. When something changes, it is recorded in the changelog. Found a stale price? Email us.

OpenAIChecked: 2026-08-19
API PricingBatch API docsPrompt caching docs

Prices are published per model on the pricing page. Batch pricing is 50% of standard.

AnthropicChecked: 2026-08-19
PricingPrompt caching docsBatch API docs

Cache write/read multipliers differ by TTL (5 min vs 1 hour). Batch pricing is 50% of standard.

GoogleChecked: 2026-08-19
Gemini API PricingContext caching docsVertex AI pricing

Google charges a storage cost per token-hour for cached content, separate from read cost. Prices differ above 200K context.

Meta (via providers)Checked: 2026-08-19
Together AI pricingFireworks pricingGroq pricing

Meta does not sell direct API access. Prices are averaged across major hosting providers (Together AI, Fireworks, Groq). Individual provider prices vary.

DeepSeekChecked: 2026-08-19
API pricing

Prices can vary significantly during peak hours. Listed prices are standard rates.

Mistral AIChecked: 2026-08-19
Pricing
xAIChecked: 2026-08-19
API pricing
CohereChecked: 2026-08-19
Pricing
RunPod (GPU)Checked: 2026-08-19
GPU pricing

Spot and on-demand prices. Community Cloud vs Secure Cloud rates differ.

Vast.ai (GPU)Checked: 2026-08-19
GPU marketplace

Marketplace pricing — varies by listing. Listed prices are representative averages.

Lambda Labs (GPU)Checked: 2026-08-19
GPU Cloud pricing

See the methodology page for how these prices are used in calculations.