How much does Llama 4 70B cost?

Meta has not published per-token API pricing for Llama 4 70B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Llama 4 70B's context window?

Llama 4 70B supports a context window of 128K tokens.

Is Llama 4 70B open source?

Llama 4 70B ships with open weights under the Llama 4 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Llama 4 70B released?

Llama 4 70B was released on Apr 5, 2025 by Meta.

How much does Llama 4 70B cost?

Meta has not published per-token API pricing for Llama 4 70B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Llama 4 70B's context window?

Llama 4 70B supports a context window of 128K tokens.

Is Llama 4 70B open source?

Llama 4 70B ships with open weights under the Llama 4 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Llama 4 70B released?

Llama 4 70B was released on Apr 5, 2025 by Meta.

Open weightsMetaopentextvision

Llama 4 70B

Meta's mid-tier Llama 4, the practical workhorse for self-hosted deployments.

UpdatedApr 30, 2026

Quick facts

Released: Apr 2025
Context: 128K tokens
Output / 1M: Pricing not published
License: Llama 4 Community License

About Llama 4 70B

Llama 4 70B is the variant most enterprises actually deploy. Fits comfortably on a single H100 80GB after quantization, runs at production speed with vLLM, and clears the quality bar for most internal tooling.

Benchmarks

Published scores from Meta's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval

Python coding pass@1

MMLU

Broad academic knowledge

GPQA

Graduate-level reasoning

SWE-bench

Real software-engineering tasks

Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.

Capabilities

Strengths

Self-hostable on commodity hardware
Strong all-rounder
Mature tooling (vLLM, SGLang)

Tracked weaknesses

Custom license
Trails frontier closed models

Pricing

Per-million-token rates as published by Meta.

Per-token pricing not yet published for Llama 4 70B. Check the official provider site for current tiers.

Call Llama 4 70B from your code

Drop-in snippet for the Meta SDK. Set your API key in the environment and run.

typescript

import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "llama-4-70b",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Best for

Tasks where Llama 4 70B ranks among LLMDex's top picks.

Compare Llama 4 70B with…

Frequently asked

How much does Llama 4 70B cost?
Meta has not published per-token API pricing for Llama 4 70B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.
What is Llama 4 70B's context window?
Llama 4 70B supports a context window of 128K tokens.
Is Llama 4 70B open source?
Llama 4 70B ships with open weights under the Llama 4 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.
When was Llama 4 70B released?
Llama 4 70B was released on Apr 5, 2025 by Meta.

Friday digest

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.