elephant-1 on Vercel AI Gateway

Elephant · Baseten

Serverless
Open Source

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

Why use elephant-1 on Vercel AI Gateway?

Vercel AI Gateway offers elephant-1. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.

Compare elephant-1 across 2 providers to find the best fit for your use case
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export AI_GATEWAY_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
Model ID
baseten/elephant-1

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="baseten/elephant-1",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "baseten/elephant-1", not the LLMReference slug "elephant-1".
  • creator/model-name e.g. kwaipilot/kat-coder-pro-v2
  • The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.

Compare elephant-1 Across Providers

ProviderInput (per 1M)Output (per 1M)
Baseten API——
Vercel AI Gateway——

Capabilities

Structured Outputs

About elephant-1

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.

Get Started

Model Specs

Released2026-10-21
Parameters9B
Context16K