LlamaLiveModel Card ↗

Llama 3.3 70B Instruct

Provider

Brightnode-hosted

Context

131,072 tokens

Pricing

$0.22 / 1M input · $0.50 / 1M output

APAC regions

Singapore

Residency

in-region

Task

Chat

Try in Playground Get API Key

APAC performance

Latency profile

	Singapore	Tokyo	Sydney
TTFT p50	27	41	34
TTFT p95	44	66	57
E2E latency p50	62	78	71
E2E latency p95	96	121	109

Pricing

Input: $0.22 per 1M tokens

Output: $0.50 per 1M tokens

Billing: Per-token, charged against wallet balance

Dedicated endpoint option

A100 80GB: $4.01/hr (Singapore)
H100 80GB: $14.29/hr (Singapore)

View full pricing and calculator →

Capabilities

Meta's multilingual instruction model with strong chat and reasoning quality for long-context workflows.

Best for: General chat, Code assistance, Multilingual APAC use cases, RAG pipelines, Agent backends

Quickstart code snippets

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.brightnode.cloud/v1",
    api_key="YOUR_BRIGHTNODE_API_KEY",
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Hello from APAC"}],
)

Node

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.brightnode.cloud/v1",
  apiKey: process.env.BRIGHTNODE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "meta-llama/Llama-3.3-70B-Instruct",
  messages: [{ role: "user", content: "Hello from APAC" }],
});

Other models on Brightnode

Amazon Nova 2 Lite

Proprietary models · Jakarta, Singapore, Malaysia, Thailand, Tokyo, Seoul, Taiwan

General-purpose inference

Amazon Nova Lite

Proprietary models · Singapore, Sydney, Tokyo

General-purpose inference

Amazon Nova Micro

Proprietary models · Singapore, Sydney, Tokyo

General-purpose inference

Amazon Nova Pro

Proprietary models · Singapore, Sydney, Tokyo

General-purpose inference