Llama-3.3-70B-Instruct

npm i ai @neondatabase/ai-sdk-provider

import { generateText } from "ai";
import { neon } from "@neondatabase/ai-sdk-provider";

const { text } = await generateText({
  model: neon("meta-llama-3-3-70b-instruct"),
  prompt: "Explain Serverless Postgres.",
});

console.log(text);

npm i @mastra/core

import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "neon-demo",
  name: "neon-demo",
  instructions: "You are a helpful assistant.",
  model: "neon/meta-llama-3-3-70b-instruct",
});

const { text } = await agent.generate("Explain Serverless Postgres.");
console.log(text);

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.chat.completions.create({
  model: "meta-llama-3-3-70b-instruct",
  messages: [{ role: "user", content: "Explain Serverless Postgres." }],
});
console.log(resp.choices[0].message.content);

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.chat.completions.create(
    model="meta-llama-3-3-70b-instruct",
    messages=[{"role": "user", "content": "Explain Serverless Postgres."}],
)
print(resp.choices[0].message.content)

curl "${NEON_AI_GATEWAY_BASE_URL}/v1/chat/completions" \
  -H "Authorization: Bearer ${NEON_AI_GATEWAY_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama-3-3-70b-instruct",
    "messages": [{"role": "user", "content": "Explain Serverless Postgres."}]
  }'

# 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