Skip to content
OpenSmartRoute
Model catalogue
Meta

Meta

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

Try in playground JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Meta

Llama 3.3 70B Instruct

open weights tools

Meta meta-llama/llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Input $/1M
$0.10
Output $/1M
$0.32
Context
131K
Max output
16K
Released
Dec 6, 2024
Modalities
text
Intelligence index-
Coding index12
Agentic index-

On this deployment

1 target runs this model; traffic is measured over the last 30 days.

OpenAI SDKpython
from openai import OpenAI

client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
    model="llm-onprem",   # the target on this deployment that runs Llama 3.3 70B Instruct
    messages=[{"role": "user", "content": "Summarise this in one sentence."}],
)
print(resp.model, resp.choices[0].message.content)

Price among Meta models

Input list price per million tokens; Llama 3.3 70B Instruct is the 4th cheapest of 8 listed.

  1. 1
    Llama 3.2 1B Instruct
    $0.03
  2. 2
    Llama 3.2 3B Instruct
    $0.05
  3. 3
    Llama 3.1 8B Instruct
    $0.05
  4. 4
    Llama 3.3 70B Instruct
    $0.10
  5. 5
    Llama 4 Scout
    $0.10
  6. 6
    Llama Guard 4 12B
    $0.18
  7. 7
    Llama 4 Maverick
    $0.20
  8. 8
    Llama 3.1 70B Instruct
    $0.40

More from Meta

Other models by the same vendor in the catalogue.