Goliath 120B pricing
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... This page tracks 1 listing in total. Highlighted lows are $3.75 per million input and $7.50 per million output (see table for which seller matches each).
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 1 offer is listed for Goliath 120B. Best input in this view: Openrouter.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $3.75 | $7.50 | — | — |
Input vs output · 1M tokens
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Goliath 120B cost scales with traffic.
0.375000¢ / req
0.375000¢ / req
Model specifications
Quick spec sheet for Goliath 120B before you dive back into pricing. Reported under Alpindale.
- Context window
- 6,144 tokens
- Max output
- 1,024 tokens
- Vision (images)
- No
- Tool / function calling
- No
- Streaming
- Yes
- Released
- Nov 2023
- Primary provider
- Alpindale
- Model family
- N/A
Compare Goliath 120B
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Goliath 120B.
Locked
Compare with
Pick a model on both sides.
Popular Goliath 120B comparisons
- Goliath 120B vs GPT-4o
Compare pricing side by side
- Goliath 120B vs GPT-4o mini
Compare pricing side by side
- Goliath 120B vs Claude Sonnet 4.6
Compare pricing side by side
- Goliath 120B vs Gemini 2.0 Flash
Compare pricing side by side
- Goliath 120B vs o3
Compare pricing side by side
- Goliath 120B vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Quick frequently asked items for Goliath 120B pricing and limits. The short model note from our index: 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....