elephant-1
No tracked provider pricing is available yet.
About
elephant-1 is a 9B open-weight decision model from Base Labs, Baseten's research lab, released October 21, 2026. It is a full fine-tune of Qwen3.5-9B that turns a state and typed questions into calibrated probabilities for choice, yes/no and score answers in a single forward pass, without generating free-form text, for routing, classification and rubric scoring. It shares mammoth-1's block-bidirectional attention and 6.21M-example training mix and takes text-only input. Weights are on Hugging Face at baselabs/elephant-1 under MIT. Baseten Model APIs serve it through the System One API (/v1/systemone) as decision-models/baseten-elephant-9b-latest, free through October 27, 2026.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Baseten API | - | - | ServerlessProvisionedPartial |
| Vercel AI Gateway | - | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Agents
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(1)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 60.3 | 0.4.1Observed 2026-10-21 | — |
Migration checks
No linked migration route is available for this model yet.
API versions
elephant-1decision-models/baseten-elephant-9b-latestbaseten/elephant-1baselabs/elephant-1Elephant-1No tracked provider pricing is available yet.