Llama 3.1 8b Instruct
by NanoGPT · family llama · listed Jul 2024W
Compact open Llama model for lightweight chat, drafting, and self-hosting
Current rates USD per 1M tokens
Input$0.0544
Output$0.085
Cache read$0.0272
Cache write—
Against the market
On the record
- Model id
meta-llama/llama-3.1-8b-instruct- Context window
- 131K tokens
- Max output
- 16K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-07-23
- Last updated
- 2024-07-23
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- Helicone$0.02 in · $0.05 out
- NovitaAI$0.02 in · $0.05 out
- Kilo Gateway$0.02 in · $0.04 out
- Inference$0.025 in · $0.025 out
- OpenRouter$0.05 in · $0.08 out
- Hugging Face$0.06 in · $0.06 out
- Cortecs$0.167 in · $0.167 out
- Pioneer$0.20 in · $0.20 out
- Merge Gateway$0.22 in · $0.22 out
- Weights & Biases$0.22 in · $0.22 out