SDKs

Demeterics is OpenAI SDK compatible—use the official OpenAI SDKs for Python, Node.js, and Go by simply changing the base URL. No custom SDK required!

GitHub Repository: Full SDK source code, examples, and curl scripts are available at github.com/bluefermion/demeterics

Quick Start

Python (OpenAI SDK)

Install the official OpenAI SDK:

pip install openai

Use Demeterics by changing the base URL:

from openai import OpenAI

# Initialize with Demeterics endpoint
client = OpenAI(
    base_url="https://api.demeterics.com/groq/v1",  # or /openai/v1, /anthropic/v1, /gemini/v1
    api_key="dmt_your_demeterics_api_key"
)

# Make requests as usual
response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

print(response.choices[0].message.content)

Streaming support:

stream = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Node.js (OpenAI SDK)

Install the official OpenAI SDK:

npm install openai

Use Demeterics by changing the base URL:

import OpenAI from 'openai';

// Initialize with Demeterics endpoint
const client = new OpenAI({
  baseURL: 'https://api.demeterics.com/groq/v1',  // or /openai/v1, /anthropic/v1, /gemini/v1
  apiKey: 'dmt_your_demeterics_api_key'
});

// Make requests as usual
const response = await client.chat.completions.create({
  model: 'llama-3.3-70b-versatile',
  messages: [
    { role: 'user', content: 'Explain quantum computing' }
  ]
});

console.log(response.choices[0].message.content);

Streaming support:

const stream = await client.chat.completions.create({
  model: 'llama-3.3-70b-versatile',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Go (OpenAI SDK)

Install the official OpenAI Go SDK:

go get github.com/openai/openai-go

Use Demeterics by changing the base URL:

package main

import (
    "context"
    "fmt"
    "github.com/openai/openai-go"
    "github.com/openai/openai-go/option"
)

func main() {
    client := openai.NewClient(
        option.WithBaseURL("https://api.demeterics.com/groq/v1"),  // or /openai/v1, /anthropic/v1, /gemini/v1
        option.WithAPIKey("dmt_your_demeterics_api_key"),
    )

    response, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
        Model: openai.F("llama-3.3-70b-versatile"),
        Messages: openai.F([]openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Explain quantum computing"),
        }),
    })

    if err != nil {
        panic(err)
    }

    fmt.Println(response.Choices[0].Message.Content)
}

Multi-Provider Support

Switch between providers by changing the base URL:

Example: Switching Providers

Python:

# Groq
groq_client = OpenAI(base_url="https://api.demeterics.com/groq/v1", api_key="dmt_...")

# OpenAI
openai_client = OpenAI(base_url="https://api.demeterics.com/openai/v1", api_key="dmt_...")

# Anthropic (uses Messages API)
anthropic_client = OpenAI(base_url="https://api.demeterics.com/anthropic/v1", api_key="dmt_...")

Node.js:

const groqClient = new OpenAI({ baseURL: 'https://api.demeterics.com/groq/v1', apiKey: 'dmt_...' });
const openaiClient = new OpenAI({ baseURL: 'https://api.demeterics.com/openai/v1', apiKey: 'dmt_...' });
const anthropicClient = new OpenAI({ baseURL: 'https://api.demeterics.com/anthropic/v1', apiKey: 'dmt_...' });

Anthropic (Claude) SDK

For Anthropic's native Messages API, use the Anthropic SDK:

Python:

pip install anthropic

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.demeterics.com/anthropic",
    api_key="dmt_your_demeterics_api_key"
)

response = client.messages.create(
    model="anthropic/claude-sonnet-4.5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

print(response.content[0].text)

Node.js:

npm install @anthropic-ai/sdk

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  baseURL: 'https://api.demeterics.com/anthropic',
  apiKey: 'dmt_your_demeterics_api_key'
});

const response = await client.messages.create({
  model: 'anthropic/claude-sonnet-4.5',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'Explain quantum computing' }
  ]
});

console.log(response.content[0].text);

Common Patterns

Error Handling

Python:

from openai import OpenAI, OpenAIError

client = OpenAI(
    base_url="https://api.demeterics.com/groq/v1",
    api_key="dmt_your_api_key"
)

try:
    response = client.chat.completions.create(
        model="llama-3.3-70b-versatile",
        messages=[{"role": "user", "content": "Hello"}]
    )
    print(response.choices[0].message.content)
except OpenAIError as e:
    print(f"Error: {e}")

Async Support

Python (async):

from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://api.demeterics.com/groq/v1",
    api_key="dmt_your_api_key"
)

async def main():
    response = await client.chat.completions.create(
        model="llama-3.3-70b-versatile",
        messages=[{"role": "user", "content": "Hello"}]
    )
    print(response.choices[0].message.content)

import asyncio
asyncio.run(main())

Environment Variables

Python:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.demeterics.com/groq/v1",
    api_key=os.environ["DEMETERICS_API_KEY"]  # From environment variable
)

Node.js:

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.demeterics.com/groq/v1',
  apiKey: process.env.DEMETERICS_API_KEY  // From environment variable
});

Framework Integrations

LangChain (Python)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.demeterics.com/groq/v1",
    api_key="dmt_your_api_key",
    model="llama-3.3-70b-versatile"
)

response = llm.invoke("Explain quantum computing")
print(response.content)

LangChain.js

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  configuration: {
    baseURL: "https://api.demeterics.com/groq/v1",
    apiKey: "dmt_your_api_key"
  },
  modelName: "llama-3.3-70b-versatile"
});

const response = await llm.invoke("Explain quantum computing");
console.log(response.content);

Automatic Tracking

All requests through Demeterics SDKs are automatically:

• ✅ Logged to BigQuery with full request/response payloads
• ✅ Tracked for token usage and costs
• ✅ Billed from your Stripe credit balance (or BYOK)
• ✅ Available in the dashboard at demeterics.com/interactions

No additional code required—just use the SDK as normal!

Conversion Tracking

Track business outcomes from your AI interactions using cohort tagging.

Step 1: Tag Prompts with Cohort ID

Add /// COHORT comments to group related interactions:

cohort_id = f"campaign-{user_id}-{int(time.time())}"

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{
        "role": "user",
        "content": f"""/// APP MarketingBot
/// FLOW email_generation
/// COHORT {cohort_id}

Write an engaging email subject for our summer sale."""
    }]
)

Step 2: Submit Business Outcomes

After collecting business metrics, submit them via API:

curl -X POST https://api.demeterics.com/api/v1/cohort/outcome \
  -H "Authorization: Bearer dmt_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "cohort_id": "campaign-user123-1701234567",
    "outcome": 1523.50,
    "outcome_v2": 45,
    "label": "24h revenue and clicks"
  }'

See Conversion Tracking Guide for full details.

Best Practices

1. Use Environment Variables: Never hardcode API keys — see Authentication Guide
2. Handle Errors: Implement try/catch for all API calls
3. Implement Retries: Use exponential backoff for rate limits
4. Monitor Usage: Check your dashboard for unexpected spikes — see Credits & Pricing
5. Rotate Keys: Create new API keys every 90 days

Related Documentation

Need Help?

• GitHub SDK Repo: github.com/bluefermion/demeterics
• Support: support@demeterics.com

Ready to integrate? Head to the Quick Start Guide to get your API key and make your first request.