Back to model shop
Meta
Rendered from D1 model snapshot · D1 read 109msCache check: checking

meta/llama-3.3-70b-instruct

Open weights
Llama-3.3-70B-Instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

This model's cache

This model page returns the exact headers below. The page and /api/models/meta--llama-3.3-70b-instruct share the model:meta--llama-3.3-70b-instruct tag, so invalidation stays scoped to this model.

Cache key/models/meta--llama-3.3-70b-instruct
Cache-Controlpublic, max-age=300, stale-while-revalidate=3600
Cache-Tagcatalogmodel:meta--llama-3.3-70b-instruct

Workers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.

export const Route = createFileRoute('/models/$modelSlug')({
  headers: () => ({
    'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
    'Cache-Tag': 'catalog,model:meta--llama-3.3-70b-instruct',
  }),
})

Invalidate this cache tag

await ctx.cache.purge({ tags: ['model:meta--llama-3.3-70b-instruct'] })

Use this when one model changes and you do not want to evict the whole catalog.

LlamaTool callingAttachmentsTemperature control
Released
Dec 6, 2024
Last updated
Dec 6, 2024
Context window
128K tokens
Max output
4.1K tokens
Open weights
Yes
Family
Llama

Starts at

Free

per 1M input tokens

Output

Free

Sellers

2

No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.

Capabilities & modalities
Reasoning
Tool calling
Structured output
Attachments
InputText
OutputText
Provider shelf
Where to get Llama-3.3-70B-Instruct

Sorted by lowest input price

ProviderInput / 1MOutput / 1MContext

GitHub Models

meta/llama-3.3-70b-instruct

FreeFree128KDocs

Nvidia

meta/llama-3.3-70b-instruct

FreeFree128KDocs
More from Meta