Llama 3.3 70B Versatile API

meta-llama/llama-3.3-70b-versatile
Llama-3.
Context
131K tokens
Input
$0.767 / 1M tokens
Output
$1.027 / 1M tokens

How to use Llama 3.3 70B Versatile API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to meta-llama/llama-3.3-70b-versatile.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "meta-llama/llama-3.3-70b-versatile",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "meta-llama/llama-3.3-70b-versatile",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/llama-3.3-70b-versatile","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Llama 3.3 70B Versatile API Pricing

TypePrice
Input
$0.767 / 1M tokens
Output
$1.027 / 1M tokens

Llama 3.3 70B Versatile Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
GPQA Diamond
50.5%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
MMLU-Pro
68.9%
Multi-discipline knowledge + reasoning (harder MMLU)SourceJuly 12, 2026

Llama 3.3 70B Versatile vs other models

ModelInputOutputContextBest for
$0.767 / 1M tokens
$1.027 / 1M tokens
131K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Llama 3.3 70B Versatile has a 131,072 tokens context window and can return up to 32,768 tokens.

Llama 3.3 70B Versatile takes text as input and returns text.

Use meta-llama/llama-3.3-70b-versatile as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Llama 3.3 70B Versatile is priced at input $0.767 / 1M tokens, output $1.027 / 1M tokens.

Yes, Llama 3.3 70B Versatile can stream responses as they are generated.

Llama 3.3 70B Versatile was built by Meta.

Start building with Llama 3.3 70B Versatile

Get API Key
1000+ models, one API.