GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

sarvam

Sarvam-M

Modello IA Uscita May 20, 2025

Modalità API: Chat^*
Finestra di contesto: 32.768 tokens
Output massimo: 32.768 tokens
Pesi aperti: Sì

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

Sarvam-M

Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.

Capacità

Finestra di contesto: 32.768 tokens
Input massimo: 8.192 tokens^*
Output massimo: 32.768 tokens
Ragionamento: Sì
Uso di strumenti: No
Pesi aperti: Sì
Modalità API: Chat^*
Licenza del modello: Apache 2.0

Modalità di input

text

Modalità di output

text

Configurazione di sistema

Specifiche dettagliate

Specifiche · 11 campi

cache creation input token cost

0^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost above 1hr

0^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost

0^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

0^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

sarvam^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

8.192^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max output tokens

32.000^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max tokens

32.000^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

0^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports reasoning

Sì^*

Ambito e condizioni

native_context

provider: sarvam^*
mode: chat^*
full_native_model_id: sarvam/sarvam-m^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Dati provvisori