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.
💰Qwen3 235B A22B Thinking 2507 FP8 is 83% cheaper than Goliath 120B
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Qwen3 235B A22B Thinking 2507 FP8 is 477% cheaper
| Spec | Goliath 120B | Qwen3 235B A22B Thinking 2507 FP8 |
|---|---|---|
| Provider | alpindale | qwen |
| Input price / 1M tokens | $3.75 | $0.65 |
| Output price / 1M tokens | $7.50 | $3.00 |
| Context window | 6k tokens | 262k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
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.