Llama-3.1-8B-Instruct
by Kitani · family llama · listed Jul 2024TW
Compact open Llama model for lightweight chat, drafting, and self-hosting
Current rates USD per 1M tokens
Input$0.049
Output$0.0765
Cache read$0.0245
Cache write—
Against the market
On the record
- Model id
meta-llama/llama-3.1-8b-instruct- Context window
- 8K tokens
- Max output
- 4K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-07-23
- Last updated
- 2024-07-23
- Provider docs
- kitani.ai/docs
Back of the envelope
≈
Also listed at
- Helicone$0.02 in · $0.05 out
- Novita AI$0.02 in · $0.05 out
- OpenRouter$0.02 in · $0.04 out
- Kilo Gateway$0.02 in · $0.04 out
- NanoGPT$0.02 in · $0.04 out
- Inference$0.025 in · $0.025 out
- Hugging Face$0.06 in · $0.06 out
- Merge Gateway$0.22 in · $0.22 out
- CoreWeave$0.22 in · $0.22 out