ZMIME
Meta · Released Sep 25, 2024

Llama-3.2-1B

Compact open Llama base model for lightweight and on-device use.

  • Open weights
Capability
—No ECI score yet
Input
$0.027per 1M tokens
Output
$0.201per 1M tokens
Context
131K8K max output
Pricing

What it costs

Input
$0.027per million tokens
Output
$0.201per million tokens
Blended (3:1)
$0.07cheaper than 93% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.154
Team assistant25M input + 5M output tokens$1.68
Production app250M input + 50M output tokens$16.80

Median of 6 paid API providers on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Llama-3.2-1B yet.

  • GPQA DiamondGraduate-level science questions23.9%
  • OTIS Mock AIME 2024–2025Competition mathematics0.6%

Scores from Epoch AI, run independently of Meta.

Specifications

The details

Lab
Meta
Released
Sep 25, 2024
Knowledge cutoff
Dec 2023
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text
Output
Text
Reasoning
No
Tool calling
No
Structured output
No
Availability
6 API providerslisted on models.dev
Same lab

More from Meta

Questions

About Llama-3.2-1B

How much does Llama-3.2-1B cost?

Llama-3.2-1B costs $0.027 input / $0.201 output per million tokens (median across 6 API providers). At a 3:1 input-to-output mix that is $0.07 per million tokens, cheaper than 93% of the 469 priced models we track.

What is the context window of Llama-3.2-1B?

Llama-3.2-1B accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.

How good is Llama-3.2-1B?

Epoch AI has not published a Capabilities Index score for Llama-3.2-1B yet. Epoch AI benchmark results: GPQA Diamond 23.9%, OTIS Mock AIME 2024–2025 0.6%.

Is Llama-3.2-1B open source?

Yes. Meta publishes the weights under the Llama 3.2 Community License licence, so it can be downloaded and self-hosted.

What inputs does Llama-3.2-1B support?

Llama-3.2-1B accepts text and replies in text. It is not a dedicated reasoning model, does not support tool calling.

When was Llama-3.2-1B released?

Meta released Llama-3.2-1B on Sep 25, 2024. Its training data runs to Dec 2023.

What are the best alternatives to Llama-3.2-1B?

The closest current models from other labs on capability, price and release date are Ministral 3B (Mistral AI, $0.10 / $0.10), Gemma 3 4B IT (Google, $0.05 / $0.10), Command R7B (Cohere, $0.037 / $0.15) and Nova Micro (Amazon, $0.035 / $0.14).