Llama 3.2 3B Instruct
Provider: deepinfra ·
deepinfra/meta-llama/Llama-3.2-3B-Instruct Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $0.02 |
| Output | $0.02 |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$0.02
per month
Medium
10M in / 2000k out
$0.24
per month
Large
100M in / 20000k out
$2.40
per month
Context
- Input window
- 131,072 tokens
- Max output
- 131,072 tokens
Capabilities
- ⬜ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Llama 3.2 3B Instruct with similar models
Gemma 3 4b It
deepinfra
$0.04 in
/ $0.08 out
Meta Llama 3.1 8B Instruct
deepinfra
$0.03 in
/ $0.05 out
Meta Llama 3.1 8B Instruct Turbo
deepinfra
$0.02 in
/ $0.03 out
Mistral Nemo Instruct 2407
deepinfra
$0.02 in
/ $0.04 out
NVIDIA Nemotron Nano 9B V2
deepinfra
$0.04 in
/ $0.16 out
Gpt Oss 20b
deepinfra
$0.04 in
/ $0.15 out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.