Ripple 65B Preview
Ripple 65B Preview is a large language model made by Ricursive, added to the catalog on 4 Nov 2026. It has a context window of 1,048,576 tokens and costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. It accepts text and produces text. Typical uses: reviewing long documents, summarising extensive text and tool-assisted multi-step tasks.
Price checked ยท source: OpenRouter
What Ripple 65B Preview is
Ricursive: Ripple 65B Preview is a text-in, text-out model from ricursiveAI. It accepts text and produces text, and its listed capabilities include reasoning, native tool calling, structured outputs, and response-format support. These features describe ways the model can be used in a workflow: it can process written requests, work with tools made available to it, and format responses according to supported output settings. The catalog does not identify specific tools or define the available response formats, so those details depend on the surrounding application.
The model has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. This context capacity may suit tasks that place extensive source material or a long conversation in one interaction. The output limit supports generating long responses, within the stated maximum. For tasks involving multiple steps, the listed reasoning and tool-calling support may be relevant; structured outputs and response-format support may fit workflows that need results arranged in a defined format. These capabilities do not guarantee a particular result, and the catalog provides no domain-specific performance information.
The model is described as a 65B model served in BF16. Its stated input and output are both text, with no image or audio modality listed. Together, these specifications identify a model for text-based interactions with a large context and tool and format capabilities. They can help assess whether it fits document-heavy tasks, extended exchanges, or text workflows that use tools and structured results.
Key features
- Accepts text and produces text
- Has a context window of 1,048,576 tokens
- Supports a maximum output of 131,072 tokens
- Supports native tool calling and reasoning
- Supports structured outputs and response formats
Typical uses
- Reviewing long documents
- Summarising extensive text
- Tool-assisted multi-step tasks
- Generating structured responses
Ripple 65B Preview pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.30 |
| Cached input read, per 1M tokens | $0.025 |
No price change since it was added on 4 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0027 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0036 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.015 |
Ripple 65B Preview specifications
| Model id | ricursiveai/ripple-65b-preview |
|---|---|
| Version | ripple-65b-preview-20261104 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 4 Nov 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Ripple 65B Preview yet.