Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰Z.ai: GLM Latest is 94% cheaper than Cogito v2.1 671B
⚡Z.ai: GLM Latest is 215ms faster than Cogito v2.1 671B
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Z.ai: GLM Latest is 1688% cheaper
| Spec | Cogito v2.1 671B | Z.ai: GLM Latest |
|---|---|---|
| Provider | deepcogito | ~z-ai |
| Input price / 1M tokens | $1.25 | $0.07 |
| Output price / 1M tokens | $1.25 | $1.40 |
| Context window | 164k tokens | 1049k tokens |
| Latency (p50) | 215ms | — |
| Best benchmark score | — | — |
| Open source | No | No |
A large language model with 671 billion parameters and 164K token context window designed for organizations requiring extended document analysis, complex reasoning tasks, and cost-effective processing at $1.25 per million input tokens.
This model always redirects to the latest GLM model from Z.ai.
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.