Side-by-side comparison
Goliath 120B vs Weaver (alpha)
| Goliath 120B | Weaver (alpha) | |
|---|---|---|
| Provider | Alpindale | Mancer |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 6,144 | 8,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | json_mode | json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 3.7500 | 0.7500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 7.5000 | 1.0000 |
Frequently asked questions
Which is cheaper, Goliath 120B or Weaver (alpha)?
Weaver (alpha) is cheaper than Goliath 120B on a 50/50 input/output blend by about $4.75 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Goliath 120B or Weaver (alpha)?
Weaver (alpha) has the larger context window at 8k tokens versus 6k tokens for Goliath 120B. That means Weaver (alpha) can ingest about 1.3x as much text per request.
What is the difference between Goliath 120B and Weaver (alpha)?
Goliath 120B comes from Alpindale; Weaver (alpha) comes from Mancer. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.