Meta / meta/llama-3.1-8b-instruct-16k

Llama 3.1 8B Instruct - access through LLMTR

Llama 3.1 8B Instruct is Meta's fast, efficient, small open-weight instruction model. It suits short chat, classification, data transformation, and light automation tasks that need low latency, and it supports JSON-formatted output. Both the context window and the maximum single-response output are capped at 16,384 tokens. This model does not support function calling.

Technical specifications

Canonical IDmeta/llama-3.1-8b-instruct-16k
ProviderMeta
Context window16,384 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.020000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.050000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/llama-3.1-8b-instruct-16k","messages":[{"role":"user","content":"Hello"}]}'

Related models