models

OpenAI: Text Embedding 3 Small

Markdown · JSON

OpenAI: Text Embedding 3 Small

OpenAI’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.

About the model

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.

Ailoot Ultra · Embeddings POST /v1/embeddings openai/text-embedding-3-small

openai/text-embedding-3-small

OpenAI /openai/text-embedding-3-small
Model ID
  • openai/text-embedding-3-small
  • text-embedding-3-small

Overview

OpenAI’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.

Accepted inputs
Text · token_ids
Results
embedding

Available in Ailoot · inputs & methods

Ailoot Ultra · Embeddings POST /v1/embeddings
Input types
text, token_ids
Output types
embedding
Context
8,192 tokens
Output format
json
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
openai/text-embedding-3-small
Default—
FieldinputTypestring|string[]|integer[]|integer[][]RequirementRequiredValues & 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_formatTypestringRequirementOptionalValues & limits
float
Defaultfloat
FielddimensionsTypeintegerRequirementNot supportedValues & limits
Minimum: 1
Default—
FielduserTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
Fieldsession_idTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
FieldtraceTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
FieldproviderTypeobjectRequirementOptionalValues & limits
Conditions: provider.options rejected
Default—
Input material combinations

text_to_embedding

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, input
Parameterinput_shapesContractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]
Parameterencoding_formatContractfloat
Parameterdimensions_overrideContractfalse
Parametermax_input_budget_unitsContract8192
Parametermultimodal_objectsContractfalse
Parametermaterial_typesContracttext, token_ids

Lifecycle: synchronous_json

Keep every vector index and dimension.

Multimodal model name does not admit image objects on this exact path.

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Standard rate When fast mode is selected
Flex mode
Standard rate When flex mode is selected
Maximum reasoning effort
Standard rate When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

ConfigurationRate scheduleCharge
ConfigurationBase token ratesRate scheduleBase rateCharge
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 →

Example requests

Ailoot Ultra · Embeddings

curlPython SDK
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "openai/text-embedding-3-small", "input": ["First document", "Second document"]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))
PY_RESULT
from openai import OpenAI
import os

client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.embeddings.create(model='openai/text-embedding-3-small',input=["First document","Second document"])
print(result)
for item in result.data:print(item.index,item.embedding)

Receive and save results

Ailoot Ultra · Embeddings

json

Keep all completed results

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.

If the original response needs checking

No embedding job endpoint is introduced.

Response fields
FieldType
FieldobjectTypestring
FieldmodelTypestring
Fielddata[].indexTypeinteger
Fielddata[].embeddingTypefinite float[]
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra openai/text-embedding-3-small, text-embedding-3-small

Method path aliases

Use the method paths shown above.

Related caller IDs

openai/text-embedding-3-small, text-embedding-3-small

Ailoot Ultra · Embeddings · text-embedding-3-small POST /v1/embeddings text-embedding-3-small

text-embedding-3-small

OpenAI /text-embedding-3-small
Model ID
  • openai/text-embedding-3-small
  • text-embedding-3-small

Overview

OpenAI’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.

Accepted inputs
Text
Results
embedding

Available in Ailoot · inputs & methods

Ailoot Ultra · Embeddings · text-embedding-3-small POST /v1/embeddings
Input types
text
Output types
embedding
Context
8,192 tokens
Output format
json
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
text-embedding-3-small
Default—
FieldinputTypestring|string[]|integer[]|integer[][]RequirementRequiredValues & 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_formatTypestringRequirementOptionalValues & limits
float
Defaultfloat
FielddimensionsTypeintegerRequirementNot supportedValues & limits
Minimum: 1
Default—
FielduserTypejson_valueRequirementOptionalValues & limits
Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model.
Default—
Fieldsession_idTypejson_valueRequirementOptionalValues & limits
Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model.
Default—
FieldtraceTypejson_valueRequirementOptionalValues & limits
Conditions: Optional JSON metadata; exact upstream semantics depend on the selected model.
Default—
FieldproviderTypeobjectRequirementOptionalValues & limits
Conditions: provider.options rejected
Default—
Input material combinations

text_to_embedding

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, input
Parameterinput_shapesContractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]
Parameterencoding_formatContractfloat
Parameterdimensions_overrideContractfalse
Parametermax_input_budget_unitsContract8192
Parametermultimodal_objectsContractfalse
Parametermaterial_typesContracttext
Parametertext_file_materialContractRead 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.

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Standard rate When fast mode is selected
Flex mode
Standard rate When flex mode is selected
Maximum reasoning effort
Standard rate When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

ConfigurationRate scheduleCharge
ConfigurationBase token ratesRate scheduleBase rateCharge
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 →

Example requests

Ailoot Ultra · Embeddings · text-embedding-3-small

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result
{
  "model": "text-embedding-3-small",
  "input": [
    "First document",
    "Second document"
  ],
  "encoding_format": "float"
}
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'text-embedding-3-small', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}
payload['input'] = [text]
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
for vector in result.get('data', []):
    print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))
PY_RESULT
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'text-embedding-3-small', 'input': ['First document', 'Second document'], 'encoding_format': 'float'}
payload['input'] = [text]
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'Authorization': 'Bearer PLACEHOLDER_KEY', 'Content-Type': 'application/json'}
headers['Authorization'] = 'Bearer ' + api_key
request = Request('https://api.ailoot.ai/v1/embeddings', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
for vector in result.get('data', []):
    print('Vector', vector.get('index'), json.dumps(vector.get('embedding')))

Receive and save results

Ailoot Ultra · Embeddings · text-embedding-3-small

json

Keep all completed results

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.

If the original response needs checking

No embedding job endpoint is introduced.

Response fields
FieldType
FieldobjectTypestring
FieldmodelTypestring
Fielddata[].indexTypeinteger
Fielddata[].embeddingTypefinite float[]
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra openai/text-embedding-3-small, text-embedding-3-small

Method path aliases

Use the method paths shown above.

Related caller IDs

openai/text-embedding-3-small, text-embedding-3-small

FAQ · OpenAI: Text Embedding 3 Small
What inputs and results are available?

POST /v1/embeddings · openai/text-embedding-3-small: text, token_ids → embedding

POST /v1/embeddings · text-embedding-3-small: text → embedding

Which fields does the request use?

POST /v1/embeddings · openai/text-embedding-3-small: model, input, encoding_format, provider

POST /v1/embeddings · text-embedding-3-small: model, input, encoding_format, provider

What limits apply?

POST /v1/embeddings · openai/text-embedding-3-small: ctx: 8192; input.budget.maximum: 8192 (UTF8 bytes); input.min_items: 1

POST /v1/embeddings · text-embedding-3-small: ctx: 8192; input.budget.maximum: 8192 (UTF8 bytes); input.min_items: 1

More details

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription
Choose a discounted plan for your regular requests.
Promo code: up to 50% off
Enter your code at checkout. The price updates to reflect the current promotion.
Spending in your history
The model, tokens and amount are recorded for each request.

Choose a subscription · View model prices

Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application
Add text, image, video and audio generation to paid features in your service.
Reseller licence
Send a description of your project and how you provide access. Request written terms for use and resale.
Documents on the website
The service offer, licence agreement and data processing policy are available before you connect.

Request a reseller licence · Service offer and licence agreement