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 98% cheaper than Fireworks: Ember-1
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Z.ai: GLM Latest is 4192% cheaper
| Spec | Fireworks: Ember-1 | Z.ai: GLM Latest |
|---|---|---|
| Provider | fireworks | ~z-ai |
| Input price / 1M tokens | $3.00 | $0.07 |
| Output price / 1M tokens | $15.00 | $1.40 |
| Context window | 1049k tokens | 1049k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
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.