Modelspage

Llama 3.2 3B Instruct

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

meta/llama-3.2-3b-instruct
Lab
Meta
Family
llama
Providers
6
Context
131,072
Output limit
131,072
Knowledge
2023-12
Release
2024-09-25
Updated
2024-09-25
Weights
Open
Input
Output types
Capabilities
tools, temperature

Providers

6
Providers
Eden AIMetacloudflare/@cf/meta/llama-3.2-3b-instruct80,000131,072$0.0509 / $0.335NoNoNoYes
Eden AIMetadeepinfra/meta-llama/Llama-3.2-3B-Instruct131,072131,072$0.02 / $0.02NoYesNoYes
InferenceMetameta/llama-3.2-3b-instruct16,0004,096$0.02 / $0.02NoYes-Yes
Kilo GatewayMetameta-llama/llama-3.2-3b-instruct131,072117,964$0.05 / $0.33NoNoYesYes
NanoGPTMetameta-llama/llama-3.2-3b-instruct131,0728,192$0.0306 / $0.0493NoNoNoYes
OpenRouterMetameta-llama/llama-3.2-3b-instruct131,072117,964$0.05 / $0.33NoNoYesYes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Modelspage lets you browse models, compare providers, and explore rankings. Open a model for its specifications and provider prices.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints. Specialized model types are omitted by default; the site includes all model types.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

Upstream SDK

The models.dev SDK provides typed catalog queries and upstream snapshots for offline use.

Contribute

The model catalog is stored in GitHub as TOML files organized by provider and canonical model.