Same model, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Anthropic Original creator | claude-haiku-4-5 | standardQuantization not disclosed | $1.0 | $5.0 | $0.10 | $2.0 | Verified 6h ago · Changed 6h ago More prices
|
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| Anthropic | $200/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.