GreenPT / greenpt/llama-3.3-70b-instruct-eu

Llama 3.3 70B Instruct - access through LLMTR

Llama 3.3 70B Instruct is an established open-weight instruction model with a 128,000-token context window. It does not reason by default, answering a short question in two tokens. Tool/function calling was verified over a full two-turn loop. It does not accept image input and says so honestly: an image request is refused with a `not a multimodal model` error rather than silently billed. One pricing note: input and output cost the same here — one of two rows on this provider where that holds, alongside Pixtral 12B — but the input rate is well above this provider's average, so newer and cheaper rows are usually the better fit for prompt-heavy work. Repeated prefixes are not served from a cache.