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 Flash Latest is 100% cheaper than DeepSeek R1 Distill Llama 70B
⚡Z.ai: GLM Flash Latest is 255ms faster than DeepSeek R1 Distill Llama 70B
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Z.ai: GLM Flash Latest is 22627% cheaper
| Spec | DeepSeek R1 Distill Llama 70B | Z.ai: GLM Flash Latest |
|---|---|---|
| Provider | deepseek-ai | ~z-ai |
| Input price / 1M tokens | $2.00 | $0.01 |
| Output price / 1M tokens | $2.00 | $0.18 |
| Context window | 131k tokens | 1049k tokens |
| Latency (p50) | 255ms | — |
| Best benchmark score | — | — |
| Open source | No | No |
This distilled reasoning model excels at complex problem-solving and multi-step analysis across a 131K token context, making it ideal for developers and enterprises seeking cost-effective ($2.00/1M input tokens) DeepSeek reasoning capabilities without the computational overhead of the full R1 model.
This model always redirects to the latest model in the GLM Flash family.
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.