Mammoth 1
Model Information
| Slug | mammoth-1 |
|---|---|
| LLMs.txt | View |
| Release Date | October 21, 2026 New |
Organization
| Name | BaseTen |
|---|
Model Description
Mammoth 1 is a 27B decision model from Base Labs, Baseten's research team, built on Qwen3.5-27B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits classification, routing, and scoring where you need a scored answer instead of prose. Its smaller sibling is [Elephant 1](https://openrouter.ai/baseten/elephant-1).
Available at 5 Providers
| Provider | Type | Model Name | Original Model | Input ($/1M) | Output ($/1M) | Free | Actions | |
|---|---|---|---|---|---|---|---|---|
|
AIHubMix |
Chat
Code
|
mammoth-1-free
|
mammoth-1-free
|
$0.00 | $0.00 | ||
|
OpenRouter |
Chat
Code
|
Mammoth 1
|
baseten/mammoth-1
|
$0.10 | $0.00 | ||
|
Vercel AI Gateway |
Mammoth-1
|
baseten/mammoth-1
|
$0.10 | - | |||
|
Infron |
|
Baseten: Mammoth 1
|
baseten/mammoth-1
|
$0.10 | $0.00 | ||
|
Concentrate AI |
Mammoth 1
|
mammoth-1
|
- | - |