Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
amazon.titan-embed-image-v1
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Input massimo
128 tokens*
Modalità API
Embedding*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 11 campi
input cost per image
6,0e-5*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
8,0e-7*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
bedrock*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
128*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
128*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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.*
metadata
notes
'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead.*
Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
embedding*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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
0,0*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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 vector size
1.024*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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 embedding image input
Sì*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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 image input
Sì*Ambito e condizioni
native_context
provider
bedrock*
mode
embedding*
full_native_model_id
amazon.titan-embed-image-v1*
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.*