Cerebras: Llama 3.3 70B

Name: Llama 3.3 70B API
Brand: Cerebras

deprecated

Llama 3.3 70B is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

llama-3.3-70bllama

Provider Quick start

Context

131.1K

tokens

Max output

16.4K

tokens

Input

$0.60

per 1M

Output

$0.80

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Cerebras

131.1K$0.60$0.80

Pricing

Item	Price	Unit
Input	$0.60	per 1M tokens
Output	$0.80	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: llama-3.3-70b
Family: llama
Status: deprecated
Knowledge: -
Released: -

Gateway Config

API: 2024-01-01
Auth: CEREBRAS_API_KEY
Discovery: static
Provider type: static

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@cerebras/llama-3.3-70b",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.cerebras.ai/v1

Chat completions

https://api.cerebras.ai/v1/chat/completions

Model

llama-3.3-70b

Auth env

CEREBRAS_API_KEY

Llama 3.3 70B FAQ

How much does the Llama 3.3 70B API cost?

Through Cerebras, Llama 3.3 70B costs $0.60 per 1M input tokens and $0.80 per 1M output tokens.

What is the context window of Llama 3.3 70B?

Llama 3.3 70B accepts up to 131.1K tokens of context and returns up to 16.4K output tokens on Cerebras.

What can Llama 3.3 70B do?

Llama 3.3 70B supports chat and function calling. It accepts text input.

How do I call Llama 3.3 70B through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @cerebras/llama-3.3-70b. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.