Llama 3.3 70B Instruct
Where it stands
Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.
About this model
Llama 3.3 70B Instruct is an AI model from Meta, made available through the API on December 6, 2024. It can read up to 131,072 tokens in one request, roughly 246 pages of text, and write up to 16,384 tokens in a single answer.
Through the API it costs $0.10 per million input tokens and $0.32 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.
It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (meta-llama/Llama-3.3-70B-Instruct), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →- GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.47.4%#100 of 116
- AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.5.1%#104 of 112
Where to use it
Companies that serve this model through an API: 11. Prices per million tokens, cheapest first.
| Provider | Inputi | Outputi | Contexti | Uptime (24 h)i |
|---|---|---|---|---|
DeepInfraCheapestfp8 | $0.10 | $0.32 | 128K | 97.9% |
Novitabf16 | $0.14 | $0.40 | 12K | 98.2% |
AkashMLfp8 | $0.20 | $0.52 | 128K | 99.6% |
Parasailfp8 | $0.22 | $0.50 | 128K | 98.4% |
SambaNova | $0.45 | $0.90 | 128K | 99.2% |
Groq | $0.59 | $0.79 | 128K | 99.8% |
CoreWeavefp16 | $0.71 | $0.71 | 128K | 99.6% |
Google | $0.72 | $0.72 | 128K | — |
Google | $0.72 | $0.72 | 128K | — |
Together | $1.04 | $1.04 | 128K | 98.7% |
Cloudflarefp8 | $0.29 | $2.25 | 24K | 98.2% |
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call Llama 3.3 70B Instruct through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "meta-llama/llama-3.3-70b-instruct", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="meta-llama/llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "meta-llama/llama-3.3-70b-instruct",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0.146
- Summarise a 100-page document$0.0053
- An app with 10,000 requests a day for a month$68.40
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
GPT-6 Luna ProOpenAI | $0.10 | $0.50 | 1.1M | Compare with ⇄ |
Reka EdgeReka | $0.10 | $0.10 | 16K | Compare with ⇄ |
Qwen3.5-9BAlibaba Qwen | $0.10 | $0.15 | 256K | Compare with ⇄ |
Seed-2.0-MiniByteDance Seed | $0.10 | $0.40 | 256K | Compare with ⇄ |
Step 3.5 FlashStepFun | $0.10 | $0.30 | 256K | Compare with ⇄ |
Ministral 3 3B 2512Mistral AI | $0.10 | $0.10 | 128K | Compare with ⇄ |
News about Meta
See all →Frequently asked questions
- How much does Llama 3.3 70B Instruct cost?
- Llama 3.3 70B Instruct costs $0.10 per million input tokens and $0.32 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.146.
- What is the context window of Llama 3.3 70B Instruct?
- Llama 3.3 70B Instruct can read up to 131,072 tokens in one request, about 246 pages of text. It can write up to 16,384 tokens in a single answer.
- Is Llama 3.3 70B Instruct open source?
- Yes. Its weights are published (meta-llama/Llama-3.3-70B-Instruct), so you can download it and run it on your own hardware, or use it through one of 11 API providers.
- Who makes Llama 3.3 70B Instruct?
- Llama 3.3 70B Instruct is made by Meta. It became available through the API on December 6, 2024.
- How good is Llama 3.3 70B Instruct?
- Llama 3.3 70B Instruct has an overall index of 127.3 in Epoch AI’s independent tests, ranking #118 of 136 models we track.
- Can Llama 3.3 70B Instruct read images?
- No. Llama 3.3 70B Instruct only accepts text as input.
- What are the alternatives to Llama 3.3 70B Instruct?
- Models with a similar price from other companies include GPT-6 Luna Pro, Reka Edge and Qwen3.5-9B. You can compare them side by side on this page.