{ "aboutHtml": "

O Text Embedding 3 Large Batch utiliza /v1/batches com o ID exato de modelo openai/text-embedding-3-large:batch. Defina endpoint como /v1/embeddings e forneça requests; cada item contém custom_id e um body com input como cadeia de texto ou matriz de cadeias. Mantenha os identificadores estáveis para que a aplicação possa associar os resultados a uma atualização de um índice de pesquisa.

O lote é assíncrono. Guarde o ID da operação original devolvido e utilize GET /v1/batches/{operation_id} para acompanhar essa mesma operação com o mesmo autor do pedido. Um conjunto de resultados concluído pode conter uma resposta ou um erro para cada custom_id; por isso, inspecione os resultados de cada item, além do estado global.

Guarde todos os resultados concluídos em JSONL, preservando cada custom_id e a respetiva resposta ou erro completos. Associe os vetores bem-sucedidos aos IDs dos documentos submetidos antes de atualizar o índice. Mantenha juntos a operação original e os registos dos itens, para poder investigar um item incompleto ou falhado sem perder os resultados já devolvidos.

", "aboutText": "O Text Embedding 3 Large Batch utiliza /v1/batches com o ID exato de modelo openai/text-embedding-3-large:batch. Defina endpoint como /v1/embeddings e forneça requests; cada item contém custom_id e um body com input como cadeia de texto ou matriz de cadeias. Mantenha os identificadores estáveis para que a aplicação possa associar os resultados a uma atualização de um índice de pesquisa.\n\nO lote é assíncrono. Guarde o ID da operação original devolvido e utilize GET /v1/batches/{operation_id} para acompanhar essa mesma operação com o mesmo autor do pedido. Um conjunto de resultados concluído pode conter uma resposta ou um erro para cada custom_id; por isso, inspecione os resultados de cada item, além do estado global.\n\nGuarde todos os resultados concluídos em JSONL, preservando cada custom_id e a respetiva resposta ou erro completos. Associe os vetores bem-sucedidos aos IDs dos documentos submetidos antes de atualizar o índice. Mantenha juntos a operação original e os registos dos itens, para poder investigar um item incompleto ou falhado sem perder os resultados já devolvidos.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "7a8c59fa801f0794d149a6e2004553d0fe896be99690485b872a5f5263057772", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "pt-pt", "methods": [ { "html": "
•

OpenAI: Text Embedding 3 Large (batch)

Outro /openai/text-embedding-3-large:batch

Introdução

O Text Embedding 3 Large Batch submete grupos de pedidos de embeddings textuais como um único lote da Ailoot. Acompanhe cada item através de custom_id e obtenha os resultados completos da operação original.

Entradas aceites
Texto
Resultados
embedding
Sobre o modelo

Esta descrição apresenta as capacidades do modelo. As entradas, saídas e opções disponíveis no Ailoot para o método selecionado estão indicadas abaixo.

O Text Embedding 3 Large Batch utiliza /v1/batches com o ID exato de modelo openai/text-embedding-3-large:batch. Defina endpoint como /v1/embeddings e forneça requests; cada item contém custom_id e um body com input como cadeia de texto ou matriz de cadeias. Mantenha os identificadores estáveis para que a aplicação possa associar os resultados a uma atualização de um índice de pesquisa.

O lote é assíncrono. Guarde o ID da operação original devolvido e utilize GET /v1/batches/{operation_id} para acompanhar essa mesma operação com o mesmo autor do pedido. Um conjunto de resultados concluído pode conter uma resposta ou um erro para cada custom_id; por isso, inspecione os resultados de cada item, além do estado global.

Guarde todos os resultados concluídos em JSONL, preservando cada custom_id e a respetiva resposta ou erro completos. Associe os vetores bem-sucedidos aos IDs dos documentos submetidos antes de atualizar o índice. Mantenha juntos a operação original e os registos dos itens, para poder investigar um item incompleto ou falhado sem perder os resultados já devolvidos.

Disponível no Ailoot · entradas e métodos

Ailoot Ultra · Batch POST /v1/batches
Entrada
text
Saída
embedding
CampoTipoRequisitoValores e limitesPredefinição
CampomodelTipostringRequisitoObrigatórioValores e limites
openai/text-embedding-3-large:batch
Condições: Utilize exatamente este seletor de encaminhamento do Ailoot.
Predefinição—
CampoendpointTipostringRequisitoObrigatórioValores e limites
/v1/embeddings
Condições:
Predefinição—
CamporequestsTipoarrayRequisitoObrigatórioValores e limites
Condições:
Predefinição—
Parâmetros e ciclo de vida do método
ParâmetroContrato
Parâmetrocontent_typeContratoapplication/json
ParâmetrorequiredContratomodel, endpoint, requests
ParâmetrooptionalContrato
Parâmetromaterial_typesContratotext
ParâmetroconditionsContratoUtilize exatamente este seletor de encaminhamento do Ailoot.

Ciclo de vida: asynchronous

GET /v1/batches/{operation_id} · O response.id original real, com a mesma identidade de quem efetua a chamada, a mesma chave e o mesmo grupo.

Tarifários

As referências tarifárias não acrescentam opções ao pedido. Os parâmetros suportados constam do método selecionado.

Modo rápido
Não especificado Quando o modo rápido está selecionado
Modo flex
Não especificado Quando o modo flex está selecionado
Esforço máximo de raciocínio
Não especificado Quando o esforço máximo de raciocínio usa o ajuste predefinido (default)
Preços da cache explícita
Não ativado Quando é pedida cache explícita

Tarifas Ailoot

Preços por configuração

Associe cada custo às condições apresentadas. Use uma única tarifa para cada conjunto de configurações alternativas.

ConfiguraçãoTabela de tarifasTokens de contexto, mais deTokens de contexto, até ao limite inclusiveCusto
ConfiguraçãoTarifas base por tokenTabela de tarifasTarifa baseTokens de contexto, mais de—Tokens de contexto, até ao limite inclusiveSem limite superiorCusto
Entrada · Tokens de entrada $0.00013 / 1K tokens
Saída · Tokens de saída $0 / 1K tokens
Entrada · Leitura da cache — / 1K tokens
Entrada · Escrita na cache — / 1K tokens
Entrada · Escrita na cache, 1 hora — / 1K tokens
ConfiguraçãoEscalão 1 por comprimento do pedidoTabela de tarifas—Tokens de contexto, mais de0Tokens de contexto, até ao limite inclusiveSem limite superiorCusto
Entrada · Tokens de entrada $0.00013 / 1K tokens
Saída · Tokens de saída $0 / 1K tokens
Entrada · Leitura da cache — / 1K tokens
Entrada · Escrita na cache — / 1K tokens
Entrada · Escrita na cache, 1 hora — / 1K tokens

O Ailoot reserva um montante estimado antes de um pedido. Após o resultado, liquida o custo final com base na utilização medida. No streaming, a liquidação usa o registo final de utilização. Como funcionam a reserva e a liquidação →

Exemplos de pedidos

Ailoot Ultra · Batch

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"endpoint": "/v1/embeddings", "model": "openai/text-embedding-3-large:batch", "requests": [{"custom_id": "embedding-1", "body": {"input": "The quick brown fox jumps over the lazy dog"}}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Receber e guardar os resultados

Ailoot Ultra · Batch

Guardar todos os resultados concluídos

Guarde cada resposta, ficheiro e parte de conteúdo devolvidos na íntegra.

Conserve o estado original, cada custom_id e a resposta ou o erro completos. Guarde todos os resultados concluídos de results[] em formato JSONL; não se presume a existência de uma via de carregamento ou descarregamento através de Files.

Se for necessário verificar a resposta original

Conserve o ID da operação original e consulte apenas esse lote original. Um tempo de espera excedido, um erro ou um estado desconhecido não autorizam outra criação.

Campos da resposta
CampoTipo
Camporesults[]Tipoarray
Camporesults[].custom_idTipostring
Camporesults[].responseTipoobject
Camporesults[].errorTipoobject
Erros e passos seguintes
RespostaCondiçãoPasso seguinte
Resposta400 · invalid_request_errorCondiçãoUm campo obrigatório, o seletor de modelo, o tipo ou a representação da entrada é inválido.Passo seguinteAnalise os detalhes de validação devolvidos antes de preparar um pedido separado.
RespostaCondiçãoO pedido original ou o respetivo resultado é desconhecido ou requer uma verificação.Passo seguinteMantenha os identificadores e os cabeçalhos originais; consulte apenas os registos de estado ou da biblioteca suportados. Não volte a enviar o pedido de criação.

Aliases

Aliases do modelo

Ailoot Ultra openai/text-embedding-3-large:batch

Aliases dos caminhos dos métodos

Use os caminhos dos métodos indicados acima.

IDs de chamada relacionados

openai/text-embedding-3-large:batch

", "method_identity": { "effective_request_model_id": "openai/text-embedding-3-large:batch", "fmt": "batches", "http": "POST", "path": "/v1/batches", "request_model_id": "openai/text-embedding-3-large:batch", "route_label": "Ultra" }, "method_key": "Ultra|batches|/v1/batches|openai%2Ftext-embedding-3-large%3Abatch", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Um campo obrigatório, o seletor de modelo, o tipo ou a representação da entrada é inválido.", "http_status": 400, "recovery": "Analise os detalhes de validação devolvidos antes de preparar um pedido separado.", "type": "invalid_request_error" }, { "condition": "O pedido original ou o respetivo resultado é desconhecido ou requer uma verificação.", "http_status": null, "recovery": "Mantenha os identificadores e os cabeçalhos originais; consulte apenas os registos de estado ou da biblioteca suportados. Não volte a enviar o pedido de criação.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "file_upload": null, "mode": "asynchronous", "status": [ { "http": "GET", "id_source": "actual original response.id, same caller/key/group", "path": "/v1/batches/{operation_id}" } ], "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Conserve o ID da operação original e consulte apenas esse lote original. Um tempo de espera excedido, um erro ou um estado desconhecido não autorizam outra criação.", "unknown_no_replay": true }, "outputs": { "all_results": "Conserve o estado original, cada custom_id e a resposta ou o erro completos. Guarde todos os resultados concluídos de results[] em formato JSONL; não se presume a existência de uma via de carregamento ou descarregamento através de Files.", "every_actual_output": true, "family": "batch", "fields": [ { "name": "results[]", "type": "array" }, { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response", "type": "object" }, { "name": "results[].error", "type": "object" } ] }, "parameters": [ { "conditions": "Utilize exatamente este seletor de encaminhamento do Ailoot.", "default_known": false, "enum": [ "openai/text-embedding-3-large:batch" ], "enum_known": true, "maximum_length": null, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum": [ "/v1/embeddings" ], "enum_known": true, "maximum_length": null, "name": "endpoint", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "body": { "properties": { "input": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] } }, "required": [ "input" ], "type": "object" }, "custom_id": { "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "maximum_length": null, "minItems": 1, "name": "requests", "required": true, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "endpoint": { "enum": [ "/v1/embeddings" ], "type": "string" }, "model": { "enum": [ "openai/text-embedding-3-large:batch" ], "type": "string" }, "requests": { "items": { "properties": { "body": { "properties": { "input": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] } }, "required": [ "input" ], "type": "object" }, "custom_id": { "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "minItems": 1, "type": "array" } }, "required": [ "model", "endpoint", "requests" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "endpoint": "/v1/embeddings", "model": "openai/text-embedding-3-large:batch", "requests": [ { "body": { "input": "The quick brown fox jumps over the lazy dog" }, "custom_id": "embedding-1" } ] }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilize exatamente este seletor de encaminhamento do Ailoot." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [], "required": [ "model", "endpoint", "requests" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "file_upload": null, "mode": "asynchronous", "status": [ { "http": "GET", "id_source": "O response.id original real, com a mesma identidade de quem efetua a chamada, a mesma chave e o mesmo grupo.", "path": "/v1/batches/{operation_id}" } ], "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Preserve the original operation ID and read only that original batch. A timeout, error or unknown state does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/batches" }, "method_aliases": [], "output": { "all_results": "Preserve original status, every custom_id and full response/error. Save all completed results[] as JSONL; no Files upload/download path is inferred.", "every_actual_output": true, "family": "batch", "fields": [ { "name": "results[]", "type": "array" }, { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response", "type": "object" }, { "name": "results[].error", "type": "object" } ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"endpoint\": \"/v1/embeddings\", \"model\": \"openai/text-embedding-3-large:batch\", \"requests\": [{\"custom_id\": \"embedding-1\", \"body\": {\"input\": \"The quick brown fox jumps over the lazy dog\"}}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_BATCH'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import quote\nr=json.loads(Path(\"result.json\").read_text()); operation=r[\"id\"]\nsubprocess.run([\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",\"https://api.ailoot.ai/v1/batches/\"+quote(operation,safe=\"\"),\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"],\"-D\",\"status-headers.txt\",\"-o\",\"status.json\"],check=True)\ns=json.loads(Path(\"status.json\").read_text())\nif s.get(\"status\")==\"completed\": Path(\"results.jsonl\").write_text(\"\".join(json.dumps(x,ensure_ascii=False)+\"\\n\" for x in s.get(\"results\",[])))\n# Repeat only this same original GET while pending; never repeat creation.\nPY_BATCH\n", "label": "Read the original batch and preserve every result", "language": "bash" } ], "family": "batch", "fast_multiplier": null, "flex_multiplier": null, "fmt": "batches", "http": "POST", "in": 0.13, "input": [ "text" ], "label": "Batch", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/batches", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "openai/text-embedding-3-large:batch", "route_label": "Ultra", "status_reads": [ "GET /v1/batches/{operation_id}" ], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.13, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "openai/text-embedding-3-large:batch", "nativeProvenance": { "input_facts_canonical_sha256": "67e7acfc602941d8ecfa1db2fa2173af9c1236b22f4e510377c2e3dbd19035b4", "input_html_sha256": "b0128bdb7a84b51029f7ea2629ae49c315b60bbc9e5fc293a1ec32fda3a884c2", "private_audit_sha256": "b0b7c224ef73fe3fe9c3d2c3ee8426489b4f2620c58811f65379ae86010e814c", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/pt-pt/openai-text-embedding-3-large-u003a-batch/", "description": "O Text Embedding 3 Large Batch submete grupos de pedidos de embeddings textuais como um único lote da Ailoot. Acompanhe cada item através de custom_id e obtenha os resultados completos da operação original.", "locale": "pt-pt", "md_url": "https://ailoot.ai/models/pt-pt/openai-text-embedding-3-large-u003a-batch/index.md", "title": "OpenAI: Text Embedding 3 Large (batch) — Ailoot", "url": "https://ailoot.ai/models/pt-pt/openai-text-embedding-3-large-u003a-batch/" }, "rawModel": { "about": "O Text Embedding 3 Large Batch utiliza /v1/batches com o ID exato de modelo openai/text-embedding-3-large:batch. Defina endpoint como /v1/embeddings e forneça requests; cada item contém custom_id e um body com input como cadeia de texto ou matriz de cadeias. Mantenha os identificadores estáveis para que a aplicação possa associar os resultados a uma atualização de um índice de pesquisa.\n\nO lote é assíncrono. Guarde o ID da operação original devolvido e utilize GET /v1/batches/{operation_id} para acompanhar essa mesma operação com o mesmo autor do pedido. Um conjunto de resultados concluído pode conter uma resposta ou um erro para cada custom_id; por isso, inspecione os resultados de cada item, além do estado global.\n\nGuarde todos os resultados concluídos em JSONL, preservando cada custom_id e a respetiva resposta ou erro completos. Associe os vetores bem-sucedidos aos IDs dos documentos submetidos antes de atualizar o índice. Mantenha juntos a operação original e os registos dos itens, para poder investigar um item incompleto ou falhado sem perder os resultados já devolvidos.", "alias_of": null, "aliases": [], "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" } ], "summary": "Todas as tarifas da configuração constam dos detalhes." } ], "ctx": null, "formats": [ "batches" ], "id": "openai/text-embedding-3-large:batch", "input": [ "text" ], "kind": "embedding", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "errors": [ { "condition": "Um campo obrigatório, o seletor de modelo, o tipo ou a representação da entrada é inválido.", "http_status": 400, "recovery": "Analise os detalhes de validação devolvidos antes de preparar um pedido separado.", "type": "invalid_request_error" }, { "condition": "O pedido original ou o respetivo resultado é desconhecido ou requer uma verificação.", "http_status": null, "recovery": "Mantenha os identificadores e os cabeçalhos originais; consulte apenas os registos de estado ou da biblioteca suportados. Não volte a enviar o pedido de criação.", "type": null } ], "lifecycle": { "cancel_endpoint": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "file_upload": null, "mode": "asynchronous", "status": [ { "http": "GET", "id_source": "actual original response.id, same caller/key/group", "path": "/v1/batches/{operation_id}" } ], "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Conserve o ID da operação original e consulte apenas esse lote original. Um tempo de espera excedido, um erro ou um estado desconhecido não autorizam outra criação.", "unknown_no_replay": true }, "outputs": { "all_results": "Conserve o estado original, cada custom_id e a resposta ou o erro completos. Guarde todos os resultados concluídos de results[] em formato JSONL; não se presume a existência de uma via de carregamento ou descarregamento através de Files.", "every_actual_output": true, "family": "batch", "fields": [ { "name": "results[]", "type": "array" }, { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response", "type": "object" }, { "name": "results[].error", "type": "object" } ] }, "parameters": [ { "conditions": "Utilize exatamente este seletor de encaminhamento do Ailoot.", "default_known": false, "enum": [ "openai/text-embedding-3-large:batch" ], "enum_known": true, "maximum_length": null, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum": [ "/v1/embeddings" ], "enum_known": true, "maximum_length": null, "name": "endpoint", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "body": { "properties": { "input": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] } }, "required": [ "input" ], "type": "object" }, "custom_id": { "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "maximum_length": null, "minItems": 1, "name": "requests", "required": true, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "endpoint": { "enum": [ "/v1/embeddings" ], "type": "string" }, "model": { "enum": [ "openai/text-embedding-3-large:batch" ], "type": "string" }, "requests": { "items": { "properties": { "body": { "properties": { "input": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] } }, "required": [ "input" ], "type": "object" }, "custom_id": { "type": "string" } }, "required": [ "custom_id", "body" ], "type": "object" }, "minItems": 1, "type": "array" } }, "required": [ "model", "endpoint", "requests" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": false, "body": { "endpoint": "/v1/embeddings", "model": "openai/text-embedding-3-large:batch", "requests": [ { "body": { "input": "The quick brown fox jumps over the lazy dog" }, "custom_id": "embedding-1" } ] }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Utilize exatamente este seletor de encaminhamento do Ailoot." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [], "required": [ "model", "endpoint", "requests" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "accepted_status": 202, "http": "POST", "path": "/v1/batches" }, "file_upload": null, "mode": "asynchronous", "status": [ { "http": "GET", "id_source": "O response.id original real, com a mesma identidade de quem efetua a chamada, a mesma chave e o mesmo grupo.", "path": "/v1/batches/{operation_id}" } ], "terminal": [ "completed", "failed", "expired", "cancelled" ], "unknown": "Preserve the original operation ID and read only that original batch. A timeout, error or unknown state does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/batches" }, "method_aliases": [], "output": { "all_results": "Preserve original status, every custom_id and full response/error. Save all completed results[] as JSONL; no Files upload/download path is inferred.", "every_actual_output": true, "family": "batch", "fields": [ { "name": "results[]", "type": "array" }, { "name": "results[].custom_id", "type": "string" }, { "name": "results[].response", "type": "object" }, { "name": "results[].error", "type": "object" } ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"endpoint\": \"/v1/embeddings\", \"model\": \"openai/text-embedding-3-large:batch\", \"requests\": [{\"custom_id\": \"embedding-1\", \"body\": {\"input\": \"The quick brown fox jumps over the lazy dog\"}}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_BATCH'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import quote\nr=json.loads(Path(\"result.json\").read_text()); operation=r[\"id\"]\nsubprocess.run([\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",\"https://api.ailoot.ai/v1/batches/\"+quote(operation,safe=\"\"),\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"],\"-D\",\"status-headers.txt\",\"-o\",\"status.json\"],check=True)\ns=json.loads(Path(\"status.json\").read_text())\nif s.get(\"status\")==\"completed\": Path(\"results.jsonl\").write_text(\"\".join(json.dumps(x,ensure_ascii=False)+\"\\n\" for x in s.get(\"results\",[])))\n# Repeat only this same original GET while pending; never repeat creation.\nPY_BATCH\n", "label": "Read the original batch and preserve every result", "language": "bash" } ], "family": "batch", "fast_multiplier": null, "flex_multiplier": null, "fmt": "batches", "http": "POST", "in": 0.13, "input": [ "text" ], "label": "Batch", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/batches", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "openai/text-embedding-3-large:batch", "route_label": "Ultra", "status_reads": [ "GET /v1/batches/{operation_id}" ], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.13, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.00013000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000013", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "openai/text-embedding-3-large:batch", "request_model_id": "openai/text-embedding-3-large:batch", "route_label": "Ultra" } ], "name": "OpenAI: Text Embedding 3 Large (batch)", "price": { "in": 0.13, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0.13, "sort_out": 0, "varies": true }, "short": "O Text Embedding 3 Large Batch submete grupos de pedidos de embeddings textuais como um único lote da Ailoot. Acompanhe cada item através de custom_id e obtenha os resultados completos da operação original.", "title": "OpenAI: Text Embedding 3 Large (batch)" }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "O Text Embedding 3 Large Batch submete grupos de pedidos de embeddings textuais como um único lote da Ailoot. Acompanhe cada item através de custom_id e obtenha os resultados completos da operação original.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "9b1e47e47572bb05e78d8f74881777981f94b82b3fbb99b5636e04bb740af2b8", "renderer_sha256": "8caea4544177cc2b7d2cb3356b5f07bfd3660386d75f2714a6f603fa5e2a6cd2" }, "sourceRevision": "0a7e0db75c54d9d352108e03c7b2af5b6280d136e19559e84f6498760a84ff92" }