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 0% cheaper than Baidu: ERNIE 4.5 21B A3B Thinking
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Z.ai: GLM Latest is 0% cheaper
| Spec | Baidu: ERNIE 4.5 21B A3B Thinking | Z.ai: GLM Latest |
|---|---|---|
| Provider | baidu | ~z-ai |
| Input price / 1M tokens | $0.07 | $0.07 |
| Output price / 1M tokens | $0.28 | $1.40 |
| Context window | 131k tokens | 1049k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.
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.