Meta / meta/llama-3.3-70b-instruct-12k

Llama 3.3 70B Instruct (12K) - access through LLMTR

Llama 3.3 70B Instruct is Meta's multilingual open-weight instruction model. It is a strong general-purpose option for chat, summarization, content drafting, coding help, and function-calling assistant flows. Both the context window and the maximum single-response output are capped at 12,288 tokens. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Technical specifications

Canonical IDmeta/llama-3.3-70b-instruct-12k
ProviderMeta
Context window12,288 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$0.135000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.400000

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-3.3-70b-instruct-12k","messages":[{"role":"user","content":"Hello"}]}'

Related models