GreenPT / greenpt/kimi-k3-eu

Kimi K3 - access through LLMTR

Kimi K3 has a 1,000,000-token context window, the widest and the most expensive row on this provider. It genuinely processes image input: in measurement it described a product photo correctly and its input token count rose by the image's own tokens. Tool/function calling was verified over a full two-turn loop — the model called the tool, consumed the tool result and produced a final answer. Repeated prompt prefixes are served from a cache and those input tokens bill at a quarter of the normal input rate. The model reasons by default: it spent hidden reasoning tokens even on a one-word question, and those tokens bill as output. Output costs five times input here, so price short requests from the output rate rather than the input one.

Technical specifications

Canonical IDgreenpt/kimi-k3-eu
ProviderGreenPT
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

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

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$4.027023
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$1.006756
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$20.135115

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":"greenpt/kimi-k3-eu","messages":[{"role":"user","content":"Hello"}]}'

Guides about this model

Related models