Llama 3.2 Instruct 3B API Pricing
Meta · released 2024-09-25
Pricing
Pricing not published by Artificial Analysis yet.
Benchmarks
5.7
Intelligence
#456 of 533
#456 of 533
—
Coding
3.3
Math
#234 of 249
#234 of 249
—
Tokens/sec
—
Time to first token
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Qwen2.5 Coder Instruct 7B | 5.8 | — |
| Jamba Reasoning 3B | 5.7 | — |
| Llama 2 Chat 7B | 5.7 | $0.10 |
| Llama 3.2 Instruct 3B | 5.7 | — |
| MiniCPM-V 4.6 1.3B | 5.7 | — |
| Mixtral 8x22B Instruct | 5.7 | — |
| Qwen1.5 Chat 110B | 5.7 | — |
More from Meta
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Muse Spark 1.3 (max) | 48.1 | $2.00 |
| Muse Spark 1.2 (xhigh) | 39.6 | $2.00 |
| Muse Spark 1.1 (xhigh) | 33.7 | $2.00 |
| Muse Spark | 31.3 | — |
| Muse Glimmer (high) | 17.5 | $0.637 |
| Llama 4 Maverick | 10.0 | $0.422 |
| Llama 4 Scout | 8.1 | $0.313 |
| Llama 3.3 Instruct 70B | 7.7 | $0.712 |
See Llama 3.2 Instruct 3B on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Llama 3.2 Instruct 3B?
Llama 3.2 Instruct 3B is developed by Meta, released 2024-09-25.
Is Llama 3.2 Instruct 3B's API pricing published?
No — as of the last data sync (2026-09-22), Artificial Analysis has not published official API pricing for Llama 3.2 Instruct 3B. This page updates automatically once pricing is available.
How does Llama 3.2 Instruct 3B rank on benchmarks?
Llama 3.2 Instruct 3B scores 5.7 on the Artificial Analysis Intelligence Index, ranking #456 of 533 models we track.
Where does this data come from?
Pricing and benchmark data for Llama 3.2 Instruct 3B comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.