Skip to content

Llama 3.1 70B Instruct

Llama 3.1 70B Instruct introduced context of 131.1K tokens, eight-language multilingual support, and trained tool-use capability to the open 70B parameter class. This release defined Meta's approach to open frontier models.

Tool Use
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'meta/llama-3.1-70b',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • Why was the jump to context of 131.1K tokens significant in Llama 3.1 70B Instruct?

    Llama 3 supported only 8K context. The 16x expansion to 131.1K tokens in Llama 3.1 70B Instruct lets you process entire codebases, book-length documents, and multi-hour transcripts in a single pass. This eliminates the chunking and retrieval complexity that shorter context windows require.

  • Which eight languages does Llama 3.1 70B Instruct support?

    English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Llama 3.1 70B Instruct was evaluated across more than 150 benchmark datasets spanning these languages.

  • What does trained tool use mean in practice?

    The model calls external functions, APIs, and databases as part of its reasoning process. Unlike prompt-engineered tool use, this capability was learned during training, making function calls more reliable and less dependent on careful prompt construction.

  • What is Llama Stack and how does it relate to the 70B?

    Llama Stack is Meta's standardized set of interfaces for retrieval-augmented generation and agentic application development. It was introduced alongside the 3.1 generation and provides a consistent integration layer for connecting the model to external tools and data sources.