z-ai/glm-5
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| GMICloudfp8 | $0.600 | $1.92 | 203K | 62.1% |
| DeepInfrafp4 | $0.600 | $2.08 | 203K | 99.7% |
| StreamLake | $0.650 | $2.08 | 198K | 99.9% |
| Baidufp8cache | $0.700 | $2.24 | 203K | 100% |
| DigitalOcean | $0.850 | $2.72 | 128K | 95.5% |
| SiliconFlowfp8 | $0.950 | $2.55 | 205K | 98.9% |
| Chutesfp8 | $0.950 | $2.55 | 203K | 88.4% |
| AtlasCloudfp8 | $0.950 | $3.15 | 203K | 100% |
| Amazon Bedrock | $1.00 | $3.20 | 203K | 93% |
| Friendli | $1.00 | $3.20 | 203K | 100% |
| Novitafp8 | $1.00 | $3.20 | 203K | 100% |
| Z.AIfp8 | $1.00 | $3.20 | 203K | 99.7% |
| Parasailfp8 | $1.00 | $3.20 | 203K | 97.8% |
| Together | $1.00 | $3.20 | 203K | 100% |
| Venicefp8 | $1.00 | $3.20 | 198K | — |
| Phala | $1.20 | $3.50 | 203K | — |
GLM 5 costs $0.600 per million input tokens and $1.92 per million output tokens via OpenRouter, making it 170th cheapest of 298 paid models.
GLM 5 scores 40.6 on the Artificial Analysis Intelligence Index, ranking 41st of 178 benchmarked models, with a GPQA Diamond score of 67%.
GLM 5 generates around 92 tokens per second with 304ms time-to-first-token (p50), the 75th fastest tracked model.
GLM 5 supports a 203K-token context window. It accepts text input.