Ripple 65B Preview

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

Input / output price: $0.10 / $0.30 per 1M
Context: 1M tokens
Released: Nov 4, 2026

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "ripple-65b-preview".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="ripple-65b-preview",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "ripple-65b-preview",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "ripple-65b-preview",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
TogetherAI`togetherai/ricursive-ai/Ripple-65B-Preview`	131K	$0.20/M	$0.60/M	$0.02/M	—
OpenRouter`openrouter/ricursiveai/ripple-65b-preview`	1M	$0.10/M	$0.30/M	$0.025/M

Is a provider down? OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.15 per 1M
Average output: $0.45 per 1M
Average cache read: $0.02 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.20/MTogetherAILowest$0.10/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

261tokens/sacross providers

Faster than 86% of the other 542 models on the gateway

Time to first token

Lower is better

1.2sacross providers

Faster than 60% of the other 136 models on the gateway

Response latency

Lower is better

1.0sacross providers

Faster than 69% of the other 630 models on the gateway

Benchmarks

8 published scores from 1 source, each linked to where it was published.

Published scores

Benchmark	Score	Source	Published
Terminal-Bench 2.1huggingface.co	80.5%	huggingface.co	Nov 12, 2026
SWE Bench Pro v2-Hardhuggingface.co	79.1%	huggingface.co	Nov 12, 2026
SWE-bench Verifiedhuggingface.co	76.5%	huggingface.co	Nov 12, 2026
SWE Bench Pro v1huggingface.co	61.4%	huggingface.co	Nov 12, 2026
DeepSWE v1.1huggingface.co	44.3%	huggingface.co	Nov 12, 2026

Benchmark	Score	Source	Published
GPQA Diamondhuggingface.co	85.2%	huggingface.co	Nov 12, 2026
AA-LCRhuggingface.co	75%	huggingface.co	Nov 12, 2026

Benchmark	Score	Source	Published
MMLU-Prohuggingface.co	84.2%	huggingface.co	Nov 12, 2026

Apps

Use Ripple 65B Preview in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Ripple 65B Preview FAQ

Short answers, built from the data on this page.

Ripple 65B Preview is a model from Other, released on Nov 4, 2026. Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

On the Respan gateway, Ripple 65B Preview costs from $0.10 per 1M input tokens and $0.30 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 2 providers, it costs $0.15 per 1M input tokens and $0.45 per 1M output tokens.

Ripple 65B Preview is available through 2 providers: TogetherAI and OpenRouter.

Ripple 65B Preview accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "ripple-65b-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Ripple 65B Preview has 8 published benchmark scores, including Terminal-Bench 2.1 80.5%, GPQA Diamond 85.2%, and MMLU-Pro 84.2%. Each score links to where it was published; the data is collected by Respan.