text-embedding-3-small is OpenAI’s smaller third-generation text-embedding model. It converts written material into numerical vectors with 1,536 components by default. Those vectors measure relationships between texts for another search or analysis step; the model does not generate a conversational answer to the input.
Like the larger third-generation model, it supports the producer’s dimensions control for shorter embeddings. The training is designed to retain concept-representing information in a shortened vector, with the choice of size affecting the application’s quality and resource requirements. Keep the model and selected dimensions consistent across the records and queries being compared.
A practical application is code search. The maker’s guide describes representing source functions as text and embedding them, then embedding a natural-language query with the same model and comparing the resulting vectors. An illustrative result is a ranked set of relevant functions linked to their source locations. For document search, the equivalent artifact is a set of passages whose text and original references remain available to the reader or next model.
Other documented uses include clustering, related-content recommendations, classification, outlier detection and measuring diversity. A focused message workflow can group similar requests or compare them with descriptions of categories. The application defines how a similarity result becomes a category, recommendation or review item; the embedding itself remains numerical data.
OpenAI specifies a maximum input of 8,192 tokens per text. Its embedding API accepts strings or tokenized input and multiple inputs in one request, rejects empty strings and applies a 300,000-token aggregate limit. Prepare long material as meaningful passages and retain the titles or definitions required to interpret them. Use a consistent set of source fields rather than embedding different kinds of records with unrelated preparation rules.
The producer returns float vectors by default and also documents base64 encoding. The guide states that OpenAI embeddings are normalized to unit length and recommends cosine similarity; a dot product can compute it and Euclidean distance gives the same ranking. If a third-generation embedding is shortened manually after it is returned, normalize that shortened vector again as the guide describes. The dimensions control avoids making manual truncation the ordinary preparation step.
Record the model identity, dimensions and source link with each vector. A useful downstream artifact is a ranked list, grouped collection or set of classification features connected to the text that produced them. Check whether the selected material actually supports the task and keep missing facts separate from semantic relatedness. The next step can then use the representation for a specific retrieval or decision workflow.
", "aboutText": "text-embedding-3-small is OpenAI’s smaller third-generation text-embedding model. It converts written material into numerical vectors with 1,536 components by default. Those vectors measure relationships between texts for another search or analysis step; the model does not generate a conversational answer to the input.\n\nLike the larger third-generation model, it supports the producer’s dimensions control for shorter embeddings. The training is designed to retain concept-representing information in a shortened vector, with the choice of size affecting the application’s quality and resource requirements. Keep the model and selected dimensions consistent across the records and queries being compared.\n\nA practical application is code search. The maker’s guide describes representing source functions as text and embedding them, then embedding a natural-language query with the same model and comparing the resulting vectors. An illustrative result is a ranked set of relevant functions linked to their source locations. For document search, the equivalent artifact is a set of passages whose text and original references remain available to the reader or next model.\n\nOther documented uses include clustering, related-content recommendations, classification, outlier detection and measuring diversity. A focused message workflow can group similar requests or compare them with descriptions of categories. The application defines how a similarity result becomes a category, recommendation or review item; the embedding itself remains numerical data.\n\nOpenAI specifies a maximum input of 8,192 tokens per text. Its embedding API accepts strings or tokenized input and multiple inputs in one request, rejects empty strings and applies a 300,000-token aggregate limit. Prepare long material as meaningful passages and retain the titles or definitions required to interpret them. Use a consistent set of source fields rather than embedding different kinds of records with unrelated preparation rules.\n\nThe producer returns float vectors by default and also documents base64 encoding. The guide states that OpenAI embeddings are normalized to unit length and recommends cosine similarity; a dot product can compute it and Euclidean distance gives the same ranking. If a third-generation embedding is shortened manually after it is returned, normalize that shortened vector again as the guide describes. The dimensions control avoids making manual truncation the ordinary preparation step.\n\nRecord the model identity, dimensions and source link with each vector. A useful downstream artifact is a ranked list, grouped collection or set of classification features connected to the text that produced them. Check whether the selected material actually supports the task and keep missing facts separate from semantic relatedness. The next step can then use the representation for a specific retrieval or decision workflow.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "272f3f65805a2a8cbf224d3f56cfa599eca0d7ba69623de0a85abc20f3d97189", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/text-embedding-3-smallOpenAI’s small third-generation text-embedding model returns 1,536-dimensional vectors by default and supports shorter representations. Use the numerical output for semantic search, code retrieval, grouping, recommendations and classification.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
text-embedding-3-small is OpenAI’s smaller third-generation text-embedding model. It converts written material into numerical vectors with 1,536 components by default. Those vectors measure relationships between texts for another search or analysis step; the model does not generate a conversational answer to the input.
Like the larger third-generation model, it supports the producer’s dimensions control for shorter embeddings. The training is designed to retain concept-representing information in a shortened vector, with the choice of size affecting the application’s quality and resource requirements. Keep the model and selected dimensions consistent across the records and queries being compared.
A practical application is code search. The maker’s guide describes representing source functions as text and embedding them, then embedding a natural-language query with the same model and comparing the resulting vectors. An illustrative result is a ranked set of relevant functions linked to their source locations. For document search, the equivalent artifact is a set of passages whose text and original references remain available to the reader or next model.
Other documented uses include clustering, related-content recommendations, classification, outlier detection and measuring diversity. A focused message workflow can group similar requests or compare them with descriptions of categories. The application defines how a similarity result becomes a category, recommendation or review item; the embedding itself remains numerical data.
OpenAI specifies a maximum input of 8,192 tokens per text. Its embedding API accepts strings or tokenized input and multiple inputs in one request, rejects empty strings and applies a 300,000-token aggregate limit. Prepare long material as meaningful passages and retain the titles or definitions required to interpret them. Use a consistent set of source fields rather than embedding different kinds of records with unrelated preparation rules.
The producer returns float vectors by default and also documents base64 encoding. The guide states that OpenAI embeddings are normalized to unit length and recommends cosine similarity; a dot product can compute it and Euclidean distance gives the same ranking. If a third-generation embedding is shortened manually after it is returned, normalize that shortened vector again as the guide describes. The dimensions control avoids making manual truncation the ordinary preparation step.
Record the model identity, dimensions and source link with each vector. A useful downstream artifact is a ranked list, grouped collection or set of classification features connected to the text that produced them. Check whether the selected material actually supports the task and keep missing facts separate from semantic relatedness. The next step can then use the representation for a specific retrieval or decision workflow.
POST /v1/embeddingstext, token_idsembedding| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/text-embedding-3-small | Default— |
Fieldinput | Typestring|string[]|integer[]|integer[][] | RequirementRequired | Values & limits Minimum items: 1 Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers. Input budget: Maximum: 8,192 · Text unit: UTF8 bytes · Token unit: token-array elements | Default— |
Fieldencoding_format | Typestring | RequirementOptional | Values & limits float | Defaultfloat |
Fielddimensions | Typeinteger | RequirementNot supported | Values & limits Minimum: 1 | Default— |
Fielduser | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldsession_id | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldtrace | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options rejected | Default— |
text_to_embedding
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameterinput_shapes | Contractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[] |
Parameterencoding_format | Contractfloat |
Parameterdimensions_override | Contractfalse |
Parametermax_input_budget_units | Contract8192 |
Parametermultimodal_objects | Contractfalse |
Parametermaterial_types | Contracttext, token_ids |
Lifecycle: synchronous_json
Keep every vector index and dimension.
Multimodal model name does not admit image objects on this exact path.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00004 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "openai/text-embedding-3-small", "input": ["First document", "Second document"]}')\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/embeddings \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.embeddings.create(model='openai/text-embedding-3-small',input=["First document","Second document"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\njson
Keep every complete returned response, file and content part.
Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.
No embedding job endpoint is introduced.
| Field | Type |
|---|---|
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fielddata[].index | Typeinteger |
Fielddata[].embedding | Typefinite float[] |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/text-embedding-3-small, text-embedding-3-small
Use the method paths shown above.
text-embedding-3-smallOpenAI’s small third-generation text-embedding model returns 1,536-dimensional vectors by default and supports shorter representations. Use the numerical output for semantic search, code retrieval, grouping, recommendations and classification.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
text-embedding-3-small is OpenAI’s smaller third-generation text-embedding model. It converts written material into numerical vectors with 1,536 components by default. Those vectors measure relationships between texts for another search or analysis step; the model does not generate a conversational answer to the input.
Like the larger third-generation model, it supports the producer’s dimensions control for shorter embeddings. The training is designed to retain concept-representing information in a shortened vector, with the choice of size affecting the application’s quality and resource requirements. Keep the model and selected dimensions consistent across the records and queries being compared.
A practical application is code search. The maker’s guide describes representing source functions as text and embedding them, then embedding a natural-language query with the same model and comparing the resulting vectors. An illustrative result is a ranked set of relevant functions linked to their source locations. For document search, the equivalent artifact is a set of passages whose text and original references remain available to the reader or next model.
Other documented uses include clustering, related-content recommendations, classification, outlier detection and measuring diversity. A focused message workflow can group similar requests or compare them with descriptions of categories. The application defines how a similarity result becomes a category, recommendation or review item; the embedding itself remains numerical data.
OpenAI specifies a maximum input of 8,192 tokens per text. Its embedding API accepts strings or tokenized input and multiple inputs in one request, rejects empty strings and applies a 300,000-token aggregate limit. Prepare long material as meaningful passages and retain the titles or definitions required to interpret them. Use a consistent set of source fields rather than embedding different kinds of records with unrelated preparation rules.
The producer returns float vectors by default and also documents base64 encoding. The guide states that OpenAI embeddings are normalized to unit length and recommends cosine similarity; a dot product can compute it and Euclidean distance gives the same ranking. If a third-generation embedding is shortened manually after it is returned, normalize that shortened vector again as the guide describes. The dimensions control avoids making manual truncation the ordinary preparation step.
Record the model identity, dimensions and source link with each vector. A useful downstream artifact is a ranked list, grouped collection or set of classification features connected to the text that produced them. Check whether the selected material actually supports the task and keep missing facts separate from semantic relatedness. The next step can then use the representation for a specific retrieval or decision workflow.
POST /v1/embeddingstextembedding| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits text-embedding-3-small | Default— |
Fieldinput | Typestring|string[]|integer[]|integer[][] | RequirementRequired | Values & limits Minimum items: 1 Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers. Input budget: Maximum: 8,192 · Text unit: UTF8 bytes · Token unit: token-array elements | Default— |
Fieldencoding_format | Typestring | RequirementOptional | Values & limits float | Defaultfloat |
Fielddimensions | Typeinteger | RequirementNot supported | Values & limits Minimum: 1 | Default— |
Fielduser | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldsession_id | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldtrace | Typejson_value | RequirementOptional | Values & limits Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model. | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options rejected | Default— |
text_to_embedding
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameterinput_shapes | Contractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[] |
Parameterencoding_format | Contractfloat |
Parameterdimensions_override | Contractfalse |
Parametermax_input_budget_units | Contract8192 |
Parametermultimodal_objects | Contractfalse |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_json
Send the exact model ID and required fields.
Keep every returned item and its original identifiers.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00004 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "text-embedding-3-small",\n "input": [\n "First document",\n "Second document"\n ],\n "encoding_format": "float"\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'text-embedding-3-small', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}\npayload['input'] = [text]\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nfor vector in result.get('data', []):\n print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'text-embedding-3-small', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}\npayload['input'] = [text]\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'Authorization': 'Bearer PLACEHOLDER_KEY', 'Content-Type': 'application/json'}\nheaders['Authorization'] = 'Bearer ' + api_key\nrequest = Request('https://api.ailoot.ai/v1/embeddings', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nfor vector in result.get('data', []):\n print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))\njson
Keep every complete returned response, file and content part.
Keep every finite vector with its original index. Preserve all dimensions and the complete usage object.
No embedding job endpoint is introduced.
| Field | Type |
|---|---|
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fielddata[].index | Typeinteger |
Fielddata[].embedding | Typefinite float[] |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/text-embedding-3-small, text-embedding-3-small
Use the method paths shown above.