z-ai/glm-4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Novitafp8 | $0.600 | $2.20 | 131K | — |
| Z.AIfp8 | $0.600 | $2.20 | 131K | 98% |
GLM 4.5 costs $0.600 per million input tokens and $2.20 per million output tokens via OpenRouter, making it 176th cheapest of 298 paid models.
GLM 4.5 scores 26.4 on the Artificial Analysis Intelligence Index, ranking 90th of 179 benchmarked models, with a GPQA Diamond score of 78%.
GLM 4.5 generates around 42 tokens per second with 1.4s time-to-first-token (p50), the 207th fastest tracked model.
GLM 4.5 supports a 131K-token context window and can output up to 98K tokens. It accepts text input.