Meta logo
Meta

Llama 3.3 70B Instruct

Call Llama 3.3 70B Instruct for general-purpose chat, reasoning, and tool use — through one OpenAI-compatible endpoint, with local payments, on the Go plan and up.

Model id llama-3.3-70b-instruct Context 131K tokens Plan Go plan & up Input $0.10 /1M Output $0.32 /1M

Last updated June 5, 2026

Pricing

Per 1M tokens, billed from your credit balance — there is no markup on usage.

DirectionPrice / 1M tokens
Input$0.10
Output$0.32
How billing works. The rate above is what usage costs against your prepaid credits on a paid plan — no per-token markup, and Zylo's flat 25% platform fee applies only when you add credits. The free Basic plan instead gives a daily allowance of Basic-tier models (10 requests/min, no card, no credits). Llama 3.3 70B Instruct requires the Go plan or higher — the free Basic plan only includes Basic-tier models. Prices update live from our catalogue.

Quickstart

Already using the OpenAI SDK? Change two lines — base_url and your key — and set the model to llama-3.3-70b-instruct.

Terminal
curl https://api.zyloai.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_ZYLO_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-instruct",
    "messages": [{"role": "user", "content": "Hello from Zylo!"}]
  }'
Python
# pip install openai
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_ZYLO_KEY",
    base_url="https://api.zyloai.net/v1",
)

response = client.chat.completions.create(
    model="llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Hello from Zylo!"}],
)
print(response.choices[0].message.content)
Node.js
// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_ZYLO_KEY",
  baseURL: "https://api.zyloai.net/v1",
});

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

Migrating?

On OpenRouter this model is meta-llama/llama-3.3-70b-instruct; on Zylo, use the id llama-3.3-70b-instruct.

Switch from OpenAI Coming from OpenRouter Use in a code agent

Frequently asked questions

How much does Llama 3.3 70B Instruct cost on Zylo?

Llama 3.3 70B Instruct is billed at its base per-token rate: $0.10 per 1M input tokens and $0.32 per 1M output tokens, deducted from your prepaid credits. There is no markup on usage — Zylo's 25% platform fee applies only when you add credits.

Which plan do I need to use Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct requires the Go plan or higher. The free Basic plan only includes Basic-tier models; paid plans (Go and up) add premium models like Llama 3.3 70B Instruct and include credits you spend on usage at the rate above.

What is the context window of Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct supports up to 131K tokens of context through Zylo's OpenAI-compatible API.

Is Llama 3.3 70B Instruct OpenAI-compatible?

Yes. Point any OpenAI SDK at https://api.zyloai.net/v1, use your Zylo API key, and set the model to llama-3.3-70b-instruct.

How do I switch Llama 3.3 70B Instruct from OpenRouter to Zylo?

On OpenRouter this model is meta-llama/llama-3.3-70b-instruct. On Zylo, use the bare id llama-3.3-70b-instruct with base URL https://api.zyloai.net/v1 — no vendor prefix.

Related reading

Guides for building on Llama 3.3 70B Instruct and other models through one API.

All Meta models Frontier model comparison Cheapest LLM APIs Multi-model routing

Start building with Llama 3.3 70B Instruct

Llama 3.3 70B Instruct runs on the Go plan or higher — create an account and upgrade to the Go plan to call it.

Create your account