Same open weights, served by 5 providers. Weights: zai-org/GLM-5.2.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Promo pricing | zai-org/GLM-5.2 | standardFP4 | $0.75 | $2.4 | $0.14 | $1.16 | Verified 3h ago · Changed 6h ago More prices
| |
Together AI | zai-org/GLM-5.2 | standardQuantization not disclosedReduced context (1M of 1M) | $1.4 | $4.4 | $0.26 | $2.15 | Verified 5h ago · Changed 5h ago | |
Mistral Deprecated | zai-glm-5-2 | standardQuantization not disclosed | $1.4 | $4.4 | $0.14 | $2.15 | Verified 5h ago · Changed 5h ago | |
Mistral Deprecated | glm-5-2 | standardQuantization not disclosed | $1.4 | $4.4 | $0.14 | $2.15 | Verified 5h ago · Changed 5h ago | |
Google Vertex AI | zai-org/glm-5.2-maas | standardQuantization not disclosedReduced context (1M of 1M) | $1.4 | $4.4 | $0.14 | $2.15 | Verified 5h ago · Changed 5h ago | |
Azure AI Foundry Fireworks on Azure | glm-5.2 | standarddata zone (US)Quantization not disclosed | $1.54 | $4.84 | $0.15 | $2.37 | Verified 3h 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 | $123/mo |
| Together AI | $228/mo |
| Mistral | $228/mo |
| Mistral | $228/mo |
| Google Vertex AI | $228/mo |
| Azure AI Foundry data zone (US) | $250.8/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.