Ricursive Ripple 65B Preview: Pricing, Specs and Limits
Ricursive Ripple 65B Preview: 65B model with native tool calling, served in BF16, 1M context, 0.10 in / 0.30 out per 1M tokens. Specs, limits and test...
By ShilpBot Team · Published · 3 min read
Ripple-65B-Preview is a 65-billion-parameter model from ricursiveAI with native tool calling, served in BF16 precision. The catalogue gives very little else, which is itself useful to know before you adopt it.
It is one of the cheapest large-context options at $0.10 per million input tokens and $0.30 per million output tokens, with a 1M-token window.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Ricursive Ripple 65B Preview quick facts
| Detail | Value |
|---|---|
| Developer | ricursiveAI |
| Model ID | ricursiveai/ripple-65b-preview |
| Added to the catalogue | 2026-11-04 |
| Type | 65B model with native tool calling, served in BF16 |
| Parameters | 65B |
| Context window | about 1M tokens (1,048,576) |
| Maximum output | 131,072 tokens |
| Input types | text |
| Price | 0.10 in / 0.30 out per 1M tokens (cached input 0.025) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Reasoning: supported, effort not adjustable.
What Ricursive Ripple 65B Preview is good for
- Cheap long-context experiments.
- Tool-calling pipelines where you want to test a low-cost model.
- Comparing a dense 65B model with mixture-of-experts competitors.
Limits of Ricursive Ripple 65B Preview
- It is labelled a preview, so behaviour and price can change.
- Little public information exists, so run your own evaluations.
- No image input or adjustable reasoning effort.
How Ricursive Ripple 65B Preview compares
- Recursive Flint: It has a larger context window (1,048,576 against 262,144 tokens); its output cap is 131,072 tokens against 235,929; it is a paid model, while Recursive Flint has a free listing.
- inclusionAI Ling 3.1 Flash: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 131,072 tokens against 262,144; it costs 0.10 input and 0.30 output per million tokens against 0.045 and 0.14.
- Reflection Beam 1.0: Both have a 1,048,576-token context window; its output cap is 131,072 tokens against 943,718; it costs 0.10 input and 0.30 output per million tokens against 0.30 and 1.00.
Calling Ricursive Ripple 65B Preview from code
Use the model ID ricursiveai/ripple-65b-preview with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "ricursiveai/ripple-65b-preview", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Ricursive Ripple 65B Preview can do
- Ask for a function call with exact arguments from a short instruction, ten times, and check the success rate.
- Paste a long document and ask a question whose answer is on page one.
- Compare its answer with Recursive Flint (free), noting that these are different companies.
What Ricursive Ripple 65B Preview costs
The catalogue lists 0.10 per million input tokens and 0.30 per million output tokens, with cached input at 0.025 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.13. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.018 before caching. If your client reuses the same prompt prefix, cached input at 0.025 per million tokens can cut the input side of that bill by about 75 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
Is ricursiveAI the same company as Recursive?
No. The catalogue lists ricursiveAI (Ripple) and Recursive (Flint) as separate providers, despite similar names.
What are the cost and limits of Ricursive Ripple 65B Preview?
As of 2026-11-16 the catalogue lists 0.10 per million input tokens and 0.30 per million output tokens. About 1M tokens (1,048,576) context window, up to 131,072 output tokens, model ID ricursiveai/ripple-65b-preview. Prices can change, so check the live model page.
