Anthropic API vs OpenAI API

Claude API uses pay-as-you-go pricing per million tokens (MTok). Haiku 4.5 costs $1 input/$5 output per MTok; Sonnet 5 costs $2 input/$10 output; Opus 5 costs $5 input/$25 output; Fable 5 costs $10 input/$50 output per MTok.

API inputs and outputs are not used for training by default, which differs from the consumer product. Retention periods and enterprise terms change, so read the current data usage policy rather than trusting a summary.

Batch processing saves 50% on API costs. Prompt caching reduces token costs by up to 90% for cached reads (charged at 80% discount compared to standard rates). Fast Mode for Opus 5 costs 2x standard pricing for up to 2.5x faster response speeds.

No. The weights are not distributed. If self-hosting is a requirement, you are looking at open-weight models instead, with the operational and quality trade-offs that implies.

Self-serve access uses usage-based tiers with automatic rate limit increases as volume grows. Enterprise customers receive custom rate limits, monthly invoice billing, and hands-on support at negotiated pricing.

Per token, with input and output priced differently and each model priced differently. Batch processing and cached input prefixes reduce it. The practical consequence is that your bill is a function of prompt design, not just of request count.

US-only inference costs 1.1x pricing for input and output tokens across all model tiers compared to standard multi-region pricing.

The same model family delivered by Microsoft under an Azure contract, with Azure identity, networking and regional controls, and a different release cadence for new models. Enterprises with an Azure agreement often choose it for procurement and data residency reasons rather than technical ones.

Cap input length, cache repeated prefixes, route easy requests to smaller models, use the batch path where latency does not matter, and set per-user limits before launch rather than after the first surprising invoice.