Baseten / baseten/mammoth-1
Mammoth-1 - access through LLMTR
Mammoth-1 is the 27B decision model from Base Labs, Baseten's research team, and the largest of the three. On /v1/systemone it answers typed questions about a state you supply (text, JSON or a conversation) without generating text: a choice from your options, a score along up to 10 levels, or the probability that a statement is true; choice and score answers come with their probability distribution. Images (PNG, JPEG or WebP) go in a user message of a conversation state. Each question must fit the 16,384-token context together with the state and images. Only input tokens are billed and the state is counted once, so ask the questions about one state in one request. The Structured Decisions documentation covers the request shape and limits.
Technical specifications
| Canonical ID | baseten/mammoth-1 |
|---|---|
| Provider | Baseten |
| Context window | 16,384 tokens |
| Operations | SYSTEM_ONE |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| SYSTEM_ONE | INPUT_TEXT | PER_1M_TOKENS | $0.100000 |
| SYSTEM_ONE | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"baseten/mammoth-1","messages":[{"role":"user","content":"Hello"}]}'Related models
- Elephant-1 baseten/elephant-1
- Joey-1 baseten/joey-1
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Qwen 3.8 27B llmtr/qwen3-8-27b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr