z-ai/glm-4.7
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp4 | $0.400 | $1.75 | 203K | 99.8% |
| StreamLake | $0.480 | $1.76 | 200K | 97.5% |
| AtlasCloudfp8 | $0.520 | $1.85 | 203K | 99.4% |
| Novitafp8 | $0.540 | $1.98 | 205K | 94.3% |
| Venicefp4 | $0.550 | $2.65 | 198K | 98.9% |
| Z.AIfp4 | $0.600 | $2.20 | 203K | 95.8% |
| $0.600 | $2.20 | 200K | 99.5% | |
| Phala | $0.850 | $3.30 | 131K | 94.7% |
| Cerebrasfp16 | $2.25 | $2.75 | 131K | 100% |
GLM 4.7 costs $0.400 per million input tokens and $1.75 per million output tokens via OpenRouter, making it 145th cheapest of 298 paid models.
GLM 4.7 scores 42.1 on the Artificial Analysis Intelligence Index, ranking 34th of 180 benchmarked models, with a GPQA Diamond score of 86%.
GLM 4.7 generates around 474 tokens per second with 564ms time-to-first-token (p50), the 4th fastest tracked model.
GLM 4.7 supports a 203K-token context window and can output up to 131K tokens. It accepts text input.