MMeta · Released Sep 25, 2024
Llama 3.2 3B Instruct
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture…
- Released
- Sep 25 2024
- Context window
- 131K 72K out
- Input / 1M tokens
- $0.051 from $0.02
- Output / 1M tokens
- $0.34 from $0.02
Where to run it
10 providers compared
Cheapest: Inference at $0.02 / $0.02 per 1M input / output tokens — 87% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Inference | $0.02 | $0.02 | — | 16K | 4K | — | Cheapest |
| LLM Gatewayno tool calling | $0.03 | $0.05 | — | 33K | 32K | — | +75% |
| DevPass (LLM Gateway)no tool calling | $0.03 | $0.05 | — | 33K | 32K | — | +75% |
| NanoGPTno tool calling | $0.031 | $0.049 | $0.015 | 131K | 8K | — | +78% |
| ParasailBF16 · no tool calling | $0.05 | $0.33 | — | 131K | 118K | 100%24h | +500% |
| Kilo Gatewayno tool calling | $0.05 | $0.33 | — | 80K | 72K | — | +500% |
| Cloudflareno tool calling | $0.051 | $0.34 | — | 80K | 72K | 100%24h | +510% |
| Cloudflare Workers AIno tool calling | $0.051 | $0.34 | — | 80K | 80K | — | +510% |
| Eden AIno tool calling | $0.051 | $0.34 | — | 80K | 131K | — | +510% |
| Pioneerno tool calling | $0.10 | $0.34 | $0.10 | 131K | 80K | — | +694% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Llama 3.2 3B Instruct. Scores appear here automatically once it does.
Specs
Details
- Model ID
meta-llama/llama-3.2-3b-instruct- Developer
- Meta
- Release date
- Sep 25, 2024 ·
- Context window
- 131,072 tokens
- Max output
- 72,000 tokens
- API price
- $0.051 / $0.34 per 1M input / output tokens
- Providers
- 10
- Input types
- text
- Reasoning
- No
- Tool calling
- No
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.