Llama 3.1 8B Instruct

Use it

Works with any OpenAI SDK: set the base URL, pass meta-llama/Llama-3.1-8B-Instruct as the model. Full reference in the docs.

curl https://tokenkiln.com/api/v1/chat/completions \
  -H "Authorization: Bearer tk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

About this model

Open weights, served from GPUs we operate. Prompts and completions are not stored or read; billing is by token counts alone. Weights, license, and benchmarks are on the Hugging Face model card.

Create an account to get an API key.