Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | zai-org/GLM-4.7 | standardFP4 | $0.40 | $1.75 | $0.08 | $0.738 | Verified 4h ago · Changed 7h ago | |
AWS Bedrock | zai.glm-4.7 | standardQuantization not disclosed | $0.60 | $2.2 | — | $1.0 | Verified 6h ago · Changed 6h 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 fp4 | $75/mo |
| AWS Bedrock | $104/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.