Llama 3.2 1B Instruct
by Cloudflare Workers AI · family llama · listed Sep 2024W
Open Llama instruction model for multilingual chat, reasoning, and coding
Current rates USD per 1M tokens
Input$0.027
Output$0.201
Cache read—
Cache write—
Against the market
On the record
- Model id
@cf/meta/llama-3.2-1b-instruct- Context window
- 60K tokens
- Max output
- 60K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-09-25
- Last updated
- 2024-09-25
- Provider docs
- developers.cloudflare.com/workers-ai/models/
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- Inference$0.01 in · $0.01 out
- OpenRouter$0.027 in · $0.201 out
- Cloudflare AI Gateway$0.027 in · $0.201 out
- Kilo Gateway$0.027 in · $0.201 out
- Pioneer$0.10 in · $0.201 out