Same open weights, served by 1 provider. Weights: zai-org/GLM-4.5.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-10-24 | zai-org/GLM-4.5 | standardFP8 | $0.38 | $1.6 | — | $0.685 | Verified 4h ago · Changed 7h ago |
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.
| DeepInfra fp8 | $70/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.