Meta: Llama 3.2 3B Instruct
by Kilo Gateway · listed Sep 2024W
Open Llama instruction model for multilingual chat, reasoning, and coding
Current rates USD per 1M tokens
Input$0.051
Output$0.34
Cache read—
Cache write—
Against the market
On the record
- Model id
meta-llama/llama-3.2-3b-instruct- Context window
- 80K tokens
- Max output
- 16K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2024-09-18
- Last updated
- 2026-03-15
- Provider docs
- kilo.ai
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- Inference$0.02 in · $0.02 out
- NovitaAI$0.03 in · $0.05 out
- LLM Gateway$0.03 in · $0.05 out
- NanoGPT$0.0306 in · $0.0493 out
- OpenRouter$0.05 in · $0.33 out
- Cloudflare Workers AI$0.0509 in · $0.335 out
- Cloudflare AI Gateway$0.051 in · $0.34 out