GTE Large EN

npm i openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NEON_AI_GATEWAY_TOKEN,
  baseURL: `${process.env.NEON_AI_GATEWAY_BASE_URL}/v1`,
});

const resp = await client.embeddings.create({
  model: "gte-large-en",
  input: ["Explain Serverless Postgres."],
  encoding_format: "float",
});
console.log(resp.data[0].embedding.length, resp.usage);

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["NEON_AI_GATEWAY_TOKEN"],
    base_url=f"{os.environ['NEON_AI_GATEWAY_BASE_URL']}/v1",
)

resp = client.embeddings.create(
    model="gte-large-en",
    input=["Explain Serverless Postgres."],
    encoding_format="float",
)
print(len(resp.data[0].embedding), resp.usage)

curl "${NEON_AI_GATEWAY_BASE_URL}/v1/embeddings" \
  -H "Authorization: Bearer ${NEON_AI_GATEWAY_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gte-large-en",
    "input": ["Explain Serverless Postgres."],
    "encoding_format": "float"
  }'

# Injected by `neon env pull` when AI Gateway is enabled on the branch (neon.ts preview.aiGateway).
# Neon injects ONLY the NEON_AI_GATEWAY_* vars (not OPENAI_*). Build the OpenAI SDK / curl
# apiKey + baseURL from them: apiKey = NEON_AI_GATEWAY_TOKEN (the bearer, nt_live_...).
#
# NEON_AI_GATEWAY_BASE_URL is the bare gateway host (no path). Append the route you need:
#   - `/v1`        - unified Chat Completions and `/v1/embeddings`
#   - `/openai/v1` - OpenAI Responses API
# @neondatabase/ai-sdk-provider and Mastra route requests automatically.

NEON_AI_GATEWAY_TOKEN=nt_live_...
NEON_AI_GATEWAY_BASE_URL=https://<branch-id>-api.ai.<cell>.<region>.<cloud>.neon.tech