Same model, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Z.ai Original creator | glm-4.5-flash | freeQuantization not disclosedReduced context (131k of 200k) | $0 | $0 | $0 | $0 | Verified 3h ago · Changed 3h 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.