Meta: Llama 3.2 3B Instruct
The Meta Llama 3.2 3B Instruct model is a text-based AI that handles input and output in the form of text. It operates within a context length of 131,072 tokens and can produce up to 117,964 completion tokens per interaction. For those looking for a balance between cost and performance, Meta Llama 3.2 3B Instruct might be worth considering, particularly given its price point of $0.05/M input token and $0.33/M output token. Its blended benchmark score of 3.9, achieved across one independent benchmark, indicates some level of capability in this area; however, it does not support tools or reasoning tasks.
Benchmark results
Independent, published benchmarks. Blended score 3.6 across 1 benchmark, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 9.4 |
- Model ID
- meta-llama/llama-3.2-3b-instruct
- Vendor
- meta-llama
- Released
- September 2024
- Tokenizer
- Llama3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 117,964 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.05/M input and $0.33/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.04 |
| A month of a busy support chatbot | 5M in / 2M out | $0.91 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-23 | $0.05 | $0.33 | 131,072 |
| 2026-07-17 | $0.05 | $0.34 | 131,072 |
Similar models
Meta: Llama Guard 4 12B
Meta: Llama 3.1 70B Instruct
Meta: Llama 3.3 70B Instruct
Meta: Llama 3.1 8B Instruct
Meta: Llama 3.2 1B Instruct
Meta: Llama 4 Maverick
Quick answers
- How much does Meta: Llama 3.2 3B Instruct cost?
- $0.05 per million input tokens and $0.33 per million output tokens.
- What is Meta: Llama 3.2 3B Instruct's context window?
- 131,072 tokens, roughly 196 pages of text in a single request.
- Does Meta: Llama 3.2 3B Instruct support tool calling?
- It supports structured output.
- Can Meta: Llama 3.2 3B Instruct process images?
- No, it is text-only on the input side.