Using mammoth-1 on Baseten API

Implementation guide · Mammoth · Baseten

ServerlessProvisioned
Open Source

Baseten API exposes mammoth-1 through model ID decision-models/baseten-mammoth-27b-latest. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-21. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Baseten API and generate an API key.
  2. 2
    Use the Baseten API SDK or REST API to call decision-models/baseten-mammoth-27b-latest — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See Baseten API documentation for integration details.

Capabilities

Structured Outputs

About mammoth-1

mammoth-1 is a 27B open-weight decision model from Base Labs, Baseten's research lab, released October 21, 2026. It is a full fine-tune of Qwen3.5-27B that returns a probability for each predefined option instead of generating text, answering choice, yes/no and score questions for classification, routing and scoring. Block-bidirectional attention in the full-attention layers lets each question see its options, and one shared-prefix prefill serves every question in a request. It was trained on 6.21M decision examples with text-only input. Weights are on Hugging Face at baselabs/mammoth-1 under MIT.

Full model details →

Model Specs

Released2026-10-21
Parameters27B
Context16K

Also available on(1)

Vercel AI Gateway
Compare all providers →

Provider

Baseten API

Baseten

San Francisco, California, United States