Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Ori
  • Labs
  • Pricing
  • Business
  • Enterprise

Explore

  • Rankings
  • Models
  • Apps
  • Providers
  • Benchmarks
  • Tools
  • Discover
  • Works With OR

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for baseten

Baseten: Elephant 1

baseten/elephant-1:free

Model weights

Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. 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 routing, classification, and scoring where you need a scored answer instead of prose. Its larger sibling is Mammoth 1Opens in new tab.

Modalities
Price
Free
Context
16K
Released
Oct 21, 2026
ActivityDocumentationFAQExplore

Activity

Token volume and request traffic to this model over time.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Baseten: Elephant 1 on OpenRouter.

  • Multimodal DecisionsGuide
  • Decisions LabLab

Explore more models

Free AI Models on OpenRouterCollectionAI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionDecision Model RankingsRanking

Frequently asked questions

Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. 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.

The Elephant 1 documentation on OpenRouter includes the Multimodal Decisions guide and the interactive Decisions Lab. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Yes. The pricing shown on this page for Elephant 1 is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.

Elephant 1 has a 16,384 token context window.

Elephant 1 accepts text and images as input and returns structured decisions.

Joey 1 and Mammoth 1 are other text models from Baseten.

Elephant 1 was released on October 21, 2026.

More models from Baseten

Joey 1

Joey 1 is a 2B decision model from Base Labs, Baseten's research team, built on Qwen3.5-2B. 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 high-volume routing, classification, and guardrail checks where latency and cost matter most. Its larger siblings are Elephant 1 and Mammoth 1.

Decisions$0.01 / $0
Mammoth 1

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.

Decisions$0.10 / $0
Elephant 1

Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. 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 routing, classification, and scoring where you need a scored answer instead of prose. Its larger sibling is Mammoth 1.

Decisions$0.035 / $0