Decision model: instead of writing text, it answers typed questions with a choice, a score or a yes/no probability. Only input tokens are billed; output is free.
Same open weights, served by 1 provider. Weights: baselabs/elephant-1.
| Provider | Their model id | Serving | Input | Source | |
|---|---|---|---|---|---|
OpenRouter | baseten/elephant-1 | standardQuantization not disclosed | $0.035 | Verified 35h ago ยท Changed 7d ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| OpenRouter | $3.5/mo |