undefined

---

from openai import OpenAI

undefined

import OpenAI from "openai";

// ── Groq ──────────────────────────────────────────────────────────────────────
const groq = new OpenAI({
  baseURL: "https://api.groq.com/openai/v1",
  apiKey: process.env.GROQ_API_KEY,
});

const completion = await groq.chat.completions.create({
  model: "llama-3.3-70b-versatile",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);

// ── OpenRouter with free model router ────────────────────────────────────────
const openrouter = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
  defaultHeaders: {
    "HTTP-Referer": "https://yourapp.com",
    "X-Title": "My App",
  },
});

// Use the free models router — automatically picks an available free model
const freeCompletion = await openrouter.chat.completions.create({
  model: "openrouter/free",
  messages: [{ role: "user", content: "What is the capital of France?" }],
});

// ── Mistral ───────────────────────────────────────────────────────────────────
const mistral = new OpenAI({
  baseURL: "https://api.mistral.ai/v1",
  apiKey: process.env.MISTRAL_API_KEY,
});

const mistralCompletion = await mistral.chat.completions.create({
  model: "mistral-small-latest",
  messages: [{ role: "user", content: "Explain async/await in JavaScript." }],
});

import requests, os

ACCOUNT_ID = os.environ["CLOUDFLARE_ACCOUNT_ID"]
API_TOKEN  = os.environ["CLOUDFLARE_API_TOKEN"]

response = requests.post(
    f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/"
    "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
    headers={"Authorization": f"Bearer {API_TOKEN}"},
    json={"messages": [{"role": "user", "content": "What is Cloudflare Workers?"}]},
)
result = response.json()
print(result["result"]["response"])

// Cloudflare Workers runtime (inside a Worker)
export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const ai = new Ai(env.AI);
    const response = await ai.run("@cf/meta/llama-3.3-70b-instruct-fp8-fast", {
      messages: [{ role: "user", content: "Hello from Workers AI!" }],
    });
    return Response.json(response);
  },
};

import requests, os

response = requests.post(
    "https://ollama.com/api/chat",
    headers={"Authorization": f"Bearer {os.environ['OLLAMA_API_KEY']}"},
    json={
        "model": "deepseek-v3.2",
        "messages": [{"role": "user", "content": "What is 2 + 2?"}],
        "stream": False,
    },
)
print(response.json()["message"]["content"])

undefined

---

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://router.huggingface.co/novita/v3/openai",
    api_key=os.environ["HF_TOKEN"],
)

response = client.chat.completions.create(
    model="meta-llama/llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Summarize the theory of relativity."}],
    max_tokens=512,
)
print(response.choices[0].message.content)

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key=os.environ["GROQ_API_KEY"],
)

with client.chat.completions.stream(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Write a short story about a robot."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

const stream = await groq.chat.completions.create({
  model: "llama-3.3-70b-versatile",
  messages: [{ role: "user", content: "Write a haiku." }],
  stream: true,
});

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

from openai import OpenAI, RateLimitError
import os

PROVIDERS = [
    {
        "name": "Groq",
        "base_url": "https://api.groq.com/openai/v1",
        "api_key": os.environ.get("GROQ_API_KEY"),
        "model": "llama-3.3-70b-versatile",
    },
    {
        "name": "Cerebras",
        "base_url": "https://api.cerebras.ai/v1",
        "api_key": os.environ.get("CEREBRAS_API_KEY"),
        "model": "llama-3.3-70b",
    },
    {
        "name": "Mistral",
        "base_url": "https://api.mistral.ai/v1",
        "api_key": os.environ.get("MISTRAL_API_KEY"),
        "model": "mistral-small-latest",
    },
    {
        "name": "OpenRouter",
        "base_url": "https://openrouter.ai/api/v1",
        "api_key": os.environ.get("OPENROUTER_API_KEY"),
        "model": "openrouter/free",
    },
]

def chat_with_fallback(messages: list[dict], **kwargs) -> str:
    for provider in PROVIDERS:
        if not provider["api_key"]:
            continue
        try:
            client = OpenAI(
                base_url=provider["base_url"],
                api_key=provider["api_key"],
            )
            response = client.chat.completions.create(
                model=provider["model"],
                messages=messages,
                **kwargs,
            )
            return response.choices[0].message.content
        except RateLimitError:
            print(f"Rate limited on {provider['name']}, trying next...")
            continue
        except Exception as e:
            print(f"Error on {provider['name']}: {e}, trying next...")
            continue
    raise RuntimeError("All providers exhausted.")

---

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
)

---

from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
import os

---

Need highest RPD?         → Cerebras (14,400 RPD)
Need smartest free model? → Gemini 2.5 Pro (if not in EU/UK/CH)
Need EU-hosted?           → Mistral AI (France)
Need most model variety?  → OpenRouter (29+ free models) or Cloudflare (48+ models)
Need fastest inference?   → Groq (purpose-built inference chips)
Need reasoning model?     → DeepSeek-R1 on Groq/OpenRouter/Kluster AI
Need vision?              → Gemini Flash, Llama 4 Scout (Groq), GLM-4.6V-Flash (Zhipu)
No rate limit concern?    → Cloudflare (10K neurons/day, compute-based)