Same open weights, served by 4 providers. Weights: zai-org/GLM-5.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-10 | zai-org/GLM-5 | flexFP4Reduced context (203k of 205k)0.8× standard | $0.48 | $1.66 | $0.096 | $0.776 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-09-10 | zai-org/GLM-5 | standardFP4Reduced context (203k of 205k) | $0.60 | $2.08 | $0.12 | $0.97 | Verified 5h ago · Changed 7h ago | |
Together AI Deprecated | zai-org/GLM-5 | standardQuantization not disclosedReduced context (203k of 205k) | $1.0 | $3.2 | — | $1.55 | Verified 7h ago · Changed 7h ago | |
AWS Bedrock | zai.glm-5 | standardQuantization not disclosedReduced context (203k of 205k) | $1.0 | $3.2 | — | $1.55 | Verified 7h ago · Changed 7h ago | |
Google Vertex AI Deprecated | zai-org/glm-5-maas | standardQuantization not disclosedReduced context (200k of 205k) | $1.0 | $3.2 | $0.10 | $1.55 | Verified 7h 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 fp4 | $101.6/mo |
| Together AI | $164/mo |
| AWS Bedrock | $164/mo |
| Google Vertex AI | $164/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.