Llama 3.3 70B Instructon Krater.ai

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model

Released December 6, 2024

Specifications

Llama 3.3 70B Instruct at a glance

Context

131.1K tokens

Max output

16.4K tokens

Input

Text

Output

Text

Input price

$0.10 / 1M

Output price

$0.32 / 1M

Knowledge cutoff

2023-12-31

Tool callingStructured outputs

Capabilities

What it is good at

Catalog capabilities

  • Generates text responses
  • Supports tool calling
  • Supports structured outputs
  • Instruction format: llama3

Good for

Long documentsUse with toolsStructured responses

Benchmarks

Catalog data, not Krater benchmarks.

Coding index score

11.9

Agentic index score

0.3

Intelligence index score

9.3

FAQ

Questions about Llama 3.3 70B Instruct

Clear answers based on the model catalog and Krater access.

Llama 3.3 70B Instruct supports a context window of 131,072 tokens.

Use Llama 3.3 70B Instruct in your API

Connect with Krater's unified API.

API access

Ready to use Llama 3.3 70B Instruct?

Access leading models in one focused workspace.