Mammoth-1 · Baseten API

What you can use today

Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.

Exact provider API ID: decision-models/baseten-mammoth-27b-latest. Up to four images as base64 data URLs or supported cloud-storage HTTPS URLs. Questions are evaluated independently. Shared input is counted once per request, plus each question; confidence measures how concentrated the answer probabilities are.

Use the exact Baseten ID. Gateway’s limits and modality tags differ. The publisher’s evaluation claims are not independent scores here. Flex and priority are optional processing settings; faster completion is not independently measured here.

Each question’s full prompt must fit 16,384 tokens, including shared input, options, formatting and images. Over-limit requests are rejected rather than shortened.

Output: Yes/no probabilities, choices and ordered scores; no written explanation. Compare decision models, limits and input costs ↗

The launch promotion has ended. Current standard input is $0.1 per million billed tokens, with no output-token charge. Native Flex is approximately 90% of default; priority defaults to twice the standard rate. Include retries when comparing the total cost.

Provider release and specifications ↗

Check availability and plans ↗

Provider documentation ↗

More setup and licensing details ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.