Fireworks AI

Fireworks AI: Llama v3.3 70B Instruct

deprecated

Llama v3.3 70B Instruct is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

accounts__fireworks__models__llama-v3p3-70b-instructllama
ProviderQuick start
Context
131.1K
tokens
Max output
16.4K
tokens
Input
$0.90
per 1M
Output
$0.90
per 1M

Activity

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

Providers

ProviderContextInput /MOutput /M
NVIDIA NIM
NVIDIA NIM
128K--
OpenRouter
OpenRouter
131.1K$0.10$0.32
Fireworks AI
Fireworks AI
131.1K$0.90$0.90

Pricing

ItemPriceUnit
Input$0.90per 1M tokens
Output$0.90per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
accounts__fireworks__models__llama-v3p3-70b-instruct
Family
llama
Status
deprecated
Knowledge
-
Released
-
Gateway Config
API
2024-01-01
Auth
FIREWORKS_API_KEY
Discovery
static
Provider type
meta

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: "@fireworks/accounts__fireworks__models__llama-v3p3-70b-instruct",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.fireworks.ai/inference/v1
Chat completions
https://api.fireworks.ai/inference/v1/chat/completions
Model
accounts__fireworks__models__llama-v3p3-70b-instruct
Auth env
FIREWORKS_API_KEY

Llama v3.3 70B Instruct FAQ

How much does the Llama v3.3 70B Instruct API cost?

Through Fireworks AI, Llama v3.3 70B Instruct costs $0.90 per 1M input tokens and $0.90 per 1M output tokens. The lowest input price in the catalog is $0.10 per 1M tokens on OpenRouter.

What is the context window of Llama v3.3 70B Instruct?

Llama v3.3 70B Instruct accepts up to 131.1K tokens of context and returns up to 16.4K output tokens on Fireworks AI.

Which providers offer Llama v3.3 70B Instruct?

Llama v3.3 70B Instruct is available from NVIDIA NIM, OpenRouter and Fireworks AI. Everstack can route between them with automatic fallback when one is unavailable.

What can Llama v3.3 70B Instruct do?

Llama v3.3 70B Instruct supports chat and function calling. It accepts text input.

How do I call Llama v3.3 70B Instruct through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @fireworks/accounts__fireworks__models__llama-v3p3-70b-instruct. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.