GeekRadar / Il banco di confronto
thinking machinesInkling-Small
Modello IA · Uscita
- Finestra di contesto
1.048.576 tokens*
- Output massimo
1.048.576 tokens*
Capacità e preferenze
Capacità generale · ECI
Stima delle capacità basata su più benchmark. Punti di indice, non una percentuale; gli intervalli mostrano l’incertezza.
130170
Inkling-Small
Inkling-Small · Intervallo 95% 147,7–152,4
Esecuzione locale
Inferenza · stima della memoria
Inkling-Small
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
- Finestra di contesto
1.048.576 tokens*
- Output massimo
1.048.576 tokens*
- Licenza del modello
Apache-2.0*
Configurazione di sistema
Specifiche dettagliate
Specifiche 1 · 4 campi
- Modalità di accesso
- Open weights (unrestricted)*
- Pesi aperti
- Sì*
- Organizzazione
- Thinking Machines*
- Paese dell’organizzazione
- United States of America*
Specifiche 2 · 26 campi
- File allegati
- Sì*
- Finestra di contesto
- 1.048.576* tokens
- Famiglia del modello
- ling*
- Licenza del modello
- Apache-2.0*
- Output massimo
- 1.048.576* tokens
- Servizio API · Hugging Face · thinkingmachines/Inkling-Small
- Provider
- Hugging Face*
- Model
- thinkingmachines/Inkling-Small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 1.048.576*
- Reasoning
- Sì*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,5*
- output
- 1,2*
- Servizio API · Arcee · thinkingmachines/inkling-small
- Provider
- Arcee*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 262.144*
- output
- 262.144*
- Reasoning
- Sì*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- No*
- Availability status
- deprecated*
- Interleaved reasoning
- field
- reasoning_content*
- Prices (USD per million tokens)
- input
- 0,5*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · Thinking Machines · thinkingmachines/Inkling-Small
- Provider
- Thinking Machines*
- Model
- thinkingmachines/Inkling-Small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 65.536*
- output
- 65.536*
- Reasoning
- Sì*
- Reasoning controls
- type
- toggle*
- type
- effort*
- values
- low*
- medium*
- high*
- xhigh*
- max*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,58*
- output
- 1,44*
- cache_read
- 0,116*
- Servizio API · Thinking Machines · thinkingmachines/Inkling-Small:peft:262144
- Provider
- Thinking Machines*
- Model
- thinkingmachines/Inkling-Small:peft:262144*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 262.144*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- toggle*
- type
- effort*
- values
- low*
- medium*
- high*
- xhigh*
- max*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,58*
- output
- 1,44*
- cache_read
- 0,116*
- Servizio API · Vercel AI Gateway · thinkingmachines/inkling-small
- Provider
- Vercel AI Gateway*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 1.000.000*
- output
- 1.000.000*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- xhigh*
- max*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · NanoGPT · thinkingmachines/Inkling-Small
- Provider
- NanoGPT*
- Model
- thinkingmachines/Inkling-Small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- input
- 524.288*
- output
- 32.768*
- Reasoning
- No*
- Tool calling
- Sì*
- Structured output
- No*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · AI/ML API · thinkingmachines/inkling-small
- Provider
- AI/ML API*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 262.144*
- Reasoning
- Sì*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Interleaved reasoning
- field
- reasoning_details*
- Prices (USD per million tokens)
- input
- 0,61364*
- output
- 1,52352*
- cache_read
- 0,122728*
- Servizio API · OpenRouter · thinkingmachines/inkling-small:free
- Provider
- OpenRouter*
- Model
- thinkingmachines/inkling-small:free*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 1.048.576*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- max*
- Tool calling
- Sì*
- Structured output
- No*
- Temperature control
- Sì*
- File attachments
- Sì*
- Servizio API · CommandCode · thinkingmachines/inkling-small
- Provider
- CommandCode*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 1.000.000*
- output
- 1.000.000*
- Reasoning
- Sì*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,5*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · Kilo Gateway · thinkingmachines/inkling-small
- Provider
- Kilo Gateway*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- max*
- Tool calling
- Sì*
- Structured output
- No*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · Deep Infra · thinkingmachines/Inkling-Small
- Provider
- Deep Infra*
- Model
- thinkingmachines/Inkling-Small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 1.048.576*
- Reasoning
- Sì*
- Tool calling
- Sì*
- Structured output
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · OpenRouter · thinkingmachines/inkling-small
- Provider
- OpenRouter*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- max*
- Tool calling
- Sì*
- Structured output
- No*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · LLMTR · thinkingmachines/inkling-small
- Provider
- LLMTR*
- Model
- thinkingmachines/inkling-small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 262.144*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- xhigh*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,58*
- output
- 1,44*
- cache_read
- 0,116*
- Servizio API · Thinking Machines · thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4
- Provider
- Thinking Machines*
- Model
- thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 262.144*
- output
- 262.144*
- Reasoning
- Sì*
- Reasoning controls
- type
- toggle*
- type
- effort*
- values
- low*
- medium*
- high*
- xhigh*
- max*
- Tool calling
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,3*
- output
- 1,2*
- cache_read
- 0,06*
- Servizio API · Eden AI · deepinfra/thinkingmachines/Inkling-Small
- Provider
- Eden AI*
- Model
- deepinfra/thinkingmachines/Inkling-Small*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- output
- 1.048.576*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- none*
- minimal*
- low*
- medium*
- high*
- max*
- Tool calling
- Sì*
- Structured output
- Sì*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Servizio API · NanoGPT · thinkingmachines/Inkling-Small:thinking
- Provider
- NanoGPT*
- Model
- thinkingmachines/Inkling-Small:thinking*
- Snapshot
- 2026-10-26*
- Token limits
- context
- 524.288*
- input
- 524.288*
- output
- 32.768*
- Reasoning
- Sì*
- Reasoning controls
- type
- effort*
- values
- minimal*
- low*
- medium*
- high*
- max*
- Tool calling
- Sì*
- Structured output
- No*
- Temperature control
- Sì*
- File attachments
- Sì*
- Prices (USD per million tokens)
- input
- 0,45*
- output
- 1,2*
- cache_read
- 0,1*
- Ragionamento
- Sì*
- Controllo della temperatura
- Sì*
- Uso di strumenti
- Sì*
* Dati provvisori