Ricursiveai

ricursiveAI/Ripple-65B-Preview

Generally availableOpen weights1M context

Summary

ricursiveAI/Ripple-65B-Preview is an open-weight language model from Ricursiveai, released on 4 Nov 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.10 per million input tokens and $0.30 per million output tokens (OpenRouter), across 1 provider we track.

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperRicursiveai
Release date4 Nov 2026 [OpenRouter]
StatusGenerally available
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters64.8B [Hugging Face]
Context window1M (1,048,576 tokens) [OpenRouter]
Max output131K tokens [OpenRouter]
InputText [OpenRouter]
OutputText [OpenRouter]
Reasoning modeNo [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputNo [OpenRouter]
Hugging FacericursiveAI/Ripple-65B-Preview [Hugging Face]

ricursiveAI/Ripple-65B-Preview API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
ricursiveai/ripple-65b-preview
$0.10$0.30$0.031MOpenRouter, 18 Nov 2026

Running ricursiveAI/Ripple-65B-Preview locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)39 GB41 GB42 GB
Q8_0 (8-bit)69 GB70 GB72 GB
FP16 / BF16 (16-bit)130 GB131 GB133 GB

At 4-bit with an 8K conversation, ricursiveAI/Ripple-65B-Preview needs about 41 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of ricursiveAI/Ripple-65B-Preview?

ricursiveAI/Ripple-65B-Preview has a context window of 1,048,576 tokens (1M) and can generate up to 131,072 tokens in a single response, according to OpenRouter.

How much does the ricursiveAI/Ripple-65B-Preview API cost?

ricursiveAI/Ripple-65B-Preview is listed from $0.10 per million input tokens and $0.30 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is ricursiveAI/Ripple-65B-Preview open source?

ricursiveAI/Ripple-65B-Preview is an open-weight model: its weights are published on Hugging Face as ricursiveAI/Ripple-65B-Preview under the apache-2.0 license. Check the license terms before commercial use.

When was ricursiveAI/Ripple-65B-Preview released?

Ricursiveai released ricursiveAI/Ripple-65B-Preview on 4 Nov 2026, according to OpenRouter.

How much VRAM does ricursiveAI/Ripple-65B-Preview need?

About 41 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 70 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
MiniMax-M3.1-FlashMiniMax19 Oct 20261M$0.07$0.30Open
MiMo-V2.6-FlashXiaomi (MiMo)22 Sept 20261M$0.14$0.28Open
DeepSeek V4.1 Flash 1017DeepSeek17 Oct 20261M$0.04$0.50Open
NVIDIA Nemotron 3.5 Super VLNVIDIA15 Oct 20261M$0.15$0.50Open
GPT-6 Luna ProOpenAI22 Sept 20261.1M$0.10$0.50–
Muse Spark 1.3 ContributorMeta2 Sept 20261M$0.10$0.20–

Change history

  • OpenRouter price changed: input $0.20 → $0.10, output $0.60 → $0.30 per 1M tokens
  • Open weights changed from none to yes
  • License changed from none to apache-2.0
  • Parameter count changed from none to 64.8B
  • Added to the directory
  • Now listed on OpenRouter

Sources