Llama 3.3 70B Instruct

Llama 3.3 70B Instruct is Meta's open-weight, text-only instruction-tuned model for multilingual assistant-style chat, commercial and research use, and synthetic data generation.

start building →

compare models

                        ... .                           .....
                 .::-++****+-::...                 ..:-+++*++-:....
              ..-+=%@@@##@@@@@%=+:.            ...-+=%@@%@%@@%%=+:..
           ..:-=@#@#@#@######@#@@%*-:         ..-=%@@@@@@@@@@@@@%%=+:.
          ..+=@####@####@@@@##@@@@@@=-.     ..-=%@@@@@@@%@@%@%@@@@%%=-:
        ..-=@@##@@#@#@@#@@@@#@@##@#@@@*:.  .:*%@@@@@%%%=***=%%%@%@@%@%*:.
        .-%@@#####@#@@%%==%%@@@@#@@@@@@%-..-%@@@@@@%*+:.....:-*%%%%@@%%=-.
       :-%@@@#@#@#@%+-:.::::-*@@@@@@@@@@%**%@@@@@@=-..      ...:*%@%@%%%%+.
      .+%@@####@@@*:..      ..:*%@@@@@@@@@@@@@@@%+:            .:+%%%@%%%=-..
     .-%@@#@@##@%-:          ...-=@@@@@@@@@@@@@=-.               .:=%%@%%==:.
    .:%@###@#@@=-.             ..:+@@@@@@@@@@%=:.                 .-=%%%%%=*:.
   ..*@##@###@%:.                 :+%@@@@@@@@%+:                   .-=%%%%%=+:
   .-@@@##@@@@-..                  :+@@@@@@@@%%+:.                 .:+%%%%%%=:.
   :*#@##@##@*:.                 ..-%%@@@@@@@@@%+:.                 .:=%%=%==*..
  .-@@@###@@%-.                  :-%@@@@@@@@@%@%%+:.                 .+=%%%%==-.
 .:*@@#@##@@+:.                ..+%@@@@@@%%@@@%%@%+:.                 :*%%%%==+.
 .:%@@##@@@%-.                .:+%@@@@@%==%%%%%@@%%+:                ..+=%=%==*:.
..-%#@@@#@@*:.               ..+%@@@@@%=::*%%%@@%@%%+:.               .-===%%=*:.
 .+@###@@@@+.                .+%%@@@@%=:...*%%@@@%@%%+..              .:*==%===-.
 .*@##@#@@%:.              .:*%%@@@%@=-.  .:+%%%@%@@%%+.               :*==%==*+.
.:*@@@@#@@%:.             .:*%@@@@@%%:.    .:*%%%%%%%%%-:              .*======+..
.:=@@#@@#@%:.           ..:*%@@%@%%=:.       :*=%%%%%%==+:.            :+======+..
.:=@@@#@@@%:.           .:*%%@%@@%=-..      ...+%%%%%%%%=+..          ..*======+..
 .*@#@@@@@%-.          .-=@@@@@@@=-.          ..+=%%%%%%%=+.           .*=====*-..
 :+@@#@@#@@+.         .-%@@@@%%%=-.            .:+%%%%%%%%=*:.        .:======*:.
 .-%@@@@@@@=-.     ..:+%@@@@%@%=-..              .+=%%%=====*:.       :+======*.
 .:*@@@@@@@@%+:....:+=%@@@@@%%=:..               ..+=%%%%==%==+:.....:+======*-.
  .:%@@@@@@@@@%=**=%@@%@@@@@%*:.                  ..-===%=%%%%==*++++*======**:
   .-%@@@@@@@@@@@@@@@@@@%@%%*:.                     .:*=%%%%============*==**:.
    .-%%@@@@@@@@@@@@@@@@%%=-.                        .:+=================*=*:..
     .:*%@@@@@@@@@@@@%@%=+:.                           .:+============*=**+:.
      ..:+=%%%%%@%%%%=*-..                              ..:+**===*=*=**++:.
        ...::-+++++-:...                                    ..:------:....
              ..                                                .. ...

input · usd / 1m tok

$0.71

output · usd / 1m tok

$0.71

context window

128ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.71
output: $0.71

providers

Different companies host Llama 3.3 70B Instruct. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Azure AI Foundry
parasail

specifications

takes text in, gives text outmeta/llama-3.3-70b

creatorMeta
model typeText generation
context window128,000 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releaseddec 6, 2024
endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="meta/llama-3.3-70b",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="meta/llama-3.3-70b",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

7.7#103 of 108 models on the gateway

coding index11.9#61 of 64
omniscience-54.2#80 of 84
gpqa49.8%#77 of 80
humanity’s last exam3.6%#85 of 87

GPQA49.8%
IFBench47.1%
LiveCodeBench28.8%
Tau226.6%
AA-LCR15.7%
AIME 20257.7%
Humanity’s Last Exam3.6%
Terminal-Bench Hard3.0%
ITBench0.6%
CritPt0.0%

Intelligence Index7.66
Omniscience Index-54.17
GDPval Elo-174.03
coding index (API)11.9
intelligence index (API)7.7

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-14.

compare Llama 3.3 70B Instruct with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

anthropic/claude-opus-5-5$4.00 / $20.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →
qwen/qwen3.8-max$2.00 / $6.00compare →

impossibl models --all →

frequently asked questions

What is Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct is Meta's open-weight, text-only instruction-tuned model for multilingual assistant-style chat, commercial and research use, and synthetic data generation. It improves on Llama 3.1 70B, approaches Llama 3.1 405B on some tasks, supports tool calling, and ships only as an instruction-tuned checkpoint.

How much does Llama 3.3 70B Instruct cost?

Llama 3.3 70B Instruct costs $0.71 per million input tokens and $0.71 per million output tokens through the Impossibl API. All rates are in USD.

view the pricing table ↑

What is the context length of Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct has a 128,000-token context window through the Impossibl API.

What inputs and outputs does Llama 3.3 70B Instruct support?

Llama 3.3 70B Instruct accepts text as input. Llama 3.3 70B Instruct returns text.

How do I use Llama 3.3 70B Instruct through an API?

Llama 3.3 70B Instruct is available through the Impossibl API. Use meta/llama-3.3-70b as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was Llama 3.3 70B Instruct released?

Meta released Llama 3.3 70B Instruct on December 6, 2024.

Creator release announcement ↗

this page describes Llama 3.3 70B Instruct as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →