DeepSeek: DeepSeek V4.1 Flash 1017 contro Ricursive: Ripple 65B Preview
Un confronto fianco a fianco tra DeepSeek: DeepSeek V4.1 Flash 1017 (0,52 USD / 1M token (≈ 0,47 €)) e Ricursive: Ripple 65B Preview (0,70 USD / 1M token (≈ 0,62 €)) con i prezzi in USD e le funzionalità aggiornati dal catalogo di api14. Entrambi funzionano con la stessa API compatibile OpenAI.
Specifiche
| DeepSeek: DeepSeek V4.1 Flash 1017 | Ricursive: Ripple 65B Preview | |
|---|---|---|
| Fornitore | DeepSeek | Ricursive |
| Ingresso | 0,52 USD / 1M token (≈ 0,47 €) | 0,70 USD / 1M token (≈ 0,62 €) |
| Uscita | 2,10 USD / 1M token (≈ 1,87 €) | 2,10 USD / 1M token (≈ 1,87 €) |
| Lettura cache | 0,01 USD / 1M token (≈ 0,01 €) | 0,18 USD / 1M token (≈ 0,16 €) |
| Finestra di contesto | 1.048.576 | 1.048.576 |
| Output massimo | 393.216 | 131.072 |
| Ingresso | text, image | text |
| Uscita | text | text |
| chiamata di strumenti | ||
| Output strutturato | ||
| Controllo del ragionamento | ||
| Aggiunto | 17 ott 2026 | 4 nov 2026 |
Differenze principali
- DeepSeek: DeepSeek V4.1 Flash 1017 costa il 25% in meno sui token di input.
- Solo DeepSeek: DeepSeek V4.1 Flash 1017 supporta output JSON strutturato.
- Solo DeepSeek: DeepSeek V4.1 Flash 1017 supporta controllo del livello di ragionamento.
- Una richiesta con 1.000 token di input e 500 di output costa 0,00158 USD con DeepSeek: DeepSeek V4.1 Flash 1017 e 0,00175 USD con Ricursive: Ripple 65B Preview.
Cambia modello con una stringa
Entrambi i modelli usano lo stesso endpoint e la stessa struttura di richiesta. Cambia il valore di model da "deepseek/deepseek-v4.1-flash-1017" a "ricursiveai/ripple-65b-preview", prompt, streaming e tool continuano a funzionare.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "ricursiveai/ripple-65b-preview",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Altri confronti
- LiquidAI: LFM3-1.7B contro Ricursive: Ripple 65B Preview
- LiquidAI: LFM3-1.7B contro Crouton Alpha
- LiquidAI: LFM3-1.7B contro Tencent: Hy4
- LiquidAI: LFM3-1.7B contro Z.ai: GLM 5.3 FlashX Legal
- Ricursive: Ripple 65B Preview contro Crouton Alpha
- Ricursive: Ripple 65B Preview contro Tencent: Hy4
- Ricursive: Ripple 65B Preview contro Z.ai: GLM 5.3 FlashX Legal
- Crouton Alpha contro Tencent: Hy4