Meta · Released Sep 25, 2024Llama-3.2-1B
Compact open Llama base model for lightweight and on-device use.
- Capability
- 102.0ECI · #147 of 148
- Input
- $0.064per 1M tokens
- Output
- $0.15per 1M tokens
- Context
- 131K8K max output
What it costs
- Input
- $0.064per million tokens
- Output
- $0.15per million tokens
- Blended (3:1)
- $0.085cheaper than 93% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.202 |
| Team assistant25M input + 5M output tokens | $2.34 |
| Production app250M input + 50M output tokens | $23.40 |
Median of 2 paid API providers on models.dev.
Independent benchmarks
#147 of 148 scored models
The shaded band is Epoch AI’s confidence range (90.7–110.3); the tick marks the median scored model.
Scores from Epoch AI, run independently of Meta.
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
- 2 API providerslisted on models.dev
More from Meta
About Llama-3.2-1B
How much does Llama-3.2-1B cost?
Llama-3.2-1B costs $0.064 input / $0.15 output per million tokens (median across 2 API providers). At a 3:1 input-to-output mix that is $0.085 per million tokens, cheaper than 93% of the 360 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 gives Llama-3.2-1B a Capabilities Index score of 102.0 (likely range 90.7–110.3), ranking it #147 of 148 models Epoch has scored. 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 8B Instruct (Mistral AI, $0.15 / $0.15), Qwen2.5-Coder-0.5B (Alibaba (Qwen), ECI 88.2, $0.10 / $0.10), Nova Lite (Amazon, $0.06 / $0.24) and Command R7B (Cohere, $0.037 / $0.15).