Llama 3.2 3B Instruct

meta-llama/llama-3.2-3b-instruct

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Llama 3.2 3B Instruct

open weights

Meta meta-llama/llama-3.2-3b-instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Input $/1M: $0.05
Output $/1M: $0.33
Context: 131K
Max output: 118K
Released: Sep 25, 2024
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Llama 3.2 3B Instruct
targets:
  - id: llama-3-2-3b-instruct
    kind: llm
    name: Llama 3.2 3B Instruct
    metadata:
      model: meta-llama/llama-3.2-3b-instruct          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: false
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000190

Price among Meta models

Input list price per million tokens; Llama 3.2 3B Instruct is the 2nd cheapest of 8 listed.

1
Llama 3.2 1B Instruct
$0.03
2
Llama 3.2 3B Instruct
$0.05
3
Llama 3.1 8B Instruct
$0.05
4
Llama 4 Scout
$0.10
5
Llama 3.3 70B Instruct
$0.10
6
Llama Guard 4 12B
$0.18
7
Llama 4 Maverick
$0.20
8
Llama 3.1 70B Instruct
$0.40

More from Meta

Other models by the same vendor in the catalogue.