Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

Meta: Llama 3.3 70B Instruct is a 70‑billion‑parameter language model from Meta that processes and generates text. It supports tool usage, offers a context window of 131 072 tokens, and provides open weights. Pricing is $0.13 per million input tokens and $0.40 per million output tokens; the model was released on 2024‑08‑01.

  • tool use
  • structured outputs
  • open-weight

At a glance

providermeta-llama
releasedAug 1, 2024
context131K
input / M$0.13

Specifications

What the API gives you

Context window
131K tokens
Max output
128K tokens
Input price
$0.13 / 1M tokens
Output price
$0.40 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Dec 31, 2023
Released
Aug 1, 2024

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.

Measured evidence

Public benchmark record

SWE-bench Verified
68.2%2025-05-16

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Self-reported scaffold plus model result. Treat it as a claim, not an independent measurement.

Open-weight model on Hugging Face.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.