Goliath 120B

Alpindale

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.

Try Now

Technical Specifications

Context Window

6,144 tokens

Max Output

1,024 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$3.75

Non-Reasoning Output

$7.50

Legacy

Made legacy on

Reason

Experimental 120B merge with 6K context and 1K max output; obsolete

Recommended Replacement

Qwen3.6 Plus