Flagship · Dec 2024

Llama 3.3 70B

Meta’s reliable workhorse — great quality-to-cost ratio for production.

By Meta · Text · Llama 3.3 Community License

Context

128K tokens

Modality

Text

Architecture

Dense FP8

License

Llama 3.3 Community License

Per 1M tokens $0.22 in · $0.50 out
Model details

Specs & substance

Developed by
Meta
Model family
Llama
Use case
Flagship
Modality
Text
Context window
128K tokens
Architecture
Dense FP8
Version
3.3
License
Llama 3.3 Community License
Pricing
$0.22 in · $0.50 out · $0.11 cache read
Released
Dec 2024
Endpoint
parasail-llama-33-70b-fp8

Meta’s reliable workhorse — great quality-to-cost ratio for production.

Llama 3.3 70B is part of the Llama family by Meta, and sits in the flagship category. It supports a 128K tokens context window and is built on a Dense FP8 architecture.

Key strengths: general, production. Parasail serves Llama 3.3 70B on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.

Integrate

Drop-in via the OpenAI SDK

Point any OpenAI-compatible client at Parasail and change the model name. That's it.

python parasail · Llama 3.3 70B
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parasail.io/v1"
)

response = client.chat.completions.create(
    model="parasail-llama-33-70b-fp8",
    messages=[
        {"role": "user", "content": "Hello, what can you do?"}
    ],
    stream=True,
    max_tokens=1000
)

for chunk in response:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)
More models

Explore the library

All models

Start building today

Instantly run any open model — popular or specialized.