Llama 3.3 70B Instruct vs GPT-4o mini

	Llama 3.3 70B Instruct	GPT-4o mini
Provider	Meta	OpenAI
Model id	`meta-llama/Llama-3.3-70B-Instruct-Turbo`	`gpt-4o-mini`
Input price	$1.35 / 1M tokens	$0.15 / 1M tokens
Output price	$1.35 / 1M tokens	$0.60 / 1M tokens
Context window	131K tokens	128K tokens
Capabilities	Chat, Tool calling, JSON mode, Multilingual	Chat, Vision, Tool calling, JSON mode
Weights	Open	Closed
Availability	Available on Inference APIs	Available
Rate limits	No daily caps; pay per request	Closed-weight. Usage tiers raise rate limits with spend.
Time to first token	1.29 s	not measured
Output speed	67.5 tokens / s	not measured

Cost for 1M input + 1M output tokens

Llama 3.3 70B Instruct

$2.7

GPT-4o mini

$0.75

GPT-4o mini is about 72% cheaper for this workload at list price. Price is only part of it: free tiers and usage tiers cap how much you can send per day, and a retired model is unavailable at any price. The "Rate limits" row above is the practical difference for a production app.

Measured speed

Speed figures for Inference APIs models are medians of three runs from a European client on 2026-09-16, against the public endpoint, using a ~120-word generation prompt (chat), a 300-character paragraph (speech) or a -second clip (transcription). External models are not measured here; treat "not measured" as unknown, not slow.

When to pick which

Llama 3.3 70B Instruct — Meta's instruction-tuned 70B model. Still served here after its retirement on Groq — the same llama-3.3-70b-versatile id works unchanged.
GPT-4o mini — Closed-weight. Usage tiers raise rate limits with spend.

Try Llama 3.3 70B Instruct

Same OpenAI request shape; the change is the base URL and key. Full parameters, aliases and pricing on the model page.

curl https://api.inferenceapis.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferenceapis.com/v1",
    api_key=os.environ["INFERENCE_API_KEY"],
)
response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! What can you do?"},
    ],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferenceapis.com/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello! What can you do?" },
  ],
});
console.log(response.choices[0].message.content);

External prices and limits come from the linked provider pages and were verified on 2026-09-16. Spotted a change? Tell us.