Skip to content

Meta · Text

Llama 3.3 70B API pricing

meta/llama-3.3-70b

General-purpose open-weight chat. Llama 3.3 70B by Meta, routed through INFRO on a Meta account you connect — alongside every other provider you run. Meta bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay Meta.

Pricing

Per 1M tokensUSD · updated 2026-10-05

Meta rate

$1.04

per 1M tokens, billed to you by Meta

INFRO adds

$0

0% markup on model spend

Per-token rates

$1.04 / 1M input tokens·$1.04 / 1M output tokens

The headline figure above is these two blended at a 3:1 input:output ratio, so one number is comparable across modalities. Your own ratio will move it.

Calling Llama 3.3 70B

POST /v1/chat/completions
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFRO_API_KEY"],
    base_url="https://api.infro.io/v1",
)

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

What this modality supports

  • Streaming
  • Tool calling
  • Structured outputs
  • Prompt caching

Frontier and open-weight language models behind an OpenAI-compatible endpoint. Streaming, tool calling, structured outputs, and vision pass straight through — and prompt caching is priced at the provider's own cached rate.

QuickstartGet a key

Alternatives for general-purpose open-weight chat

Same modality, nearest in price. All of them share the request shape above, so comparing them is a one-word change.

Work out what Llama 3.3 70B would cost you

Put your current spend on this model into the calculator and see the same workload priced here — or have us read your real usage.

Price your workloadFree price estimate