Ricursive Intelligence / ricursive/ripple-65b-preview

Ripple 65B Preview - access through LLMTR

Ripple 65B Preview is Ricursive Intelligence's open-weight, 65-billion-parameter dense model, trained with a focus on agentic coding. It takes text and answers in text, with a 131,072-token context window. It supports tool calling, including several calls in one turn, JSON object mode and JSON Schema structured output. The model decides on each request whether and how much to reason; the trace is returned in `reasoning_content`, separately from the answer, and reasoning tokens bill as output. Reasoning cannot be turned off and its level cannot be set. Repeated prompt prefixes bill at the cached-input rate. `max_tokens` is accepted up to what the context window leaves after the prompt.

Technical specifications

Canonical IDricursive/ripple-65b-preview
ProviderRicursive Intelligence
Context window131,072 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$0.200000
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.020000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.600000

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":"ricursive/ripple-65b-preview","messages":[{"role":"user","content":"Hello"}]}'

Related models