We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
OpenAI: Text Embedding Ada 002 (batch)
openai/text-embedding-ada-002:batchTry OpenAI: Text Embedding Ada 002 (batch) now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
OpenAI: Text Embedding Ada 002 (batch) at a glance
- Input price is 150% higher than the median of 34 Embeddings models.
About OpenAI: Text Embedding Ada 002 (batch)
OpenAI: Text Embedding Ada 002 (batch) is an embeddings model from OpenAI, distributed through api14 under the model id openai/text-embedding-ada-002:batch. It belongs to the embeddings category, and OpenAI describes text-embedding-ada-002 as its legacy text embedding model. If you have worked with OpenAI embeddings before, this is the same well known Ada 002 embedding model, offered here in a batch variant.
The model takes text as input and returns embeddings as output. It does not generate chat replies or free form text; its only product is a vector representation of the text you send. The context window is 8192 tokens, and the maximum output is 7372, which in practice bounds how much text can be embedded in a single request. Because the input modality is text only, images, audio and other formats are out of scope for this model.
Typical uses follow directly from those properties. Semantic search and retrieval augmented generation are the most common: you embed your documents once, embed the user query at request time, and compare vectors by similarity. The same approach supports clustering and topic discovery over large text collections, deduplication of near identical records, classification when a lightweight model is trained on top of the vectors, and recommendation or "more like this" features. Batch embedding jobs, such as indexing a document store or refreshing a vector database, are a natural fit given the batch variant.
You call it through api14's OpenAI-compatible API using the model id openai/text-embedding-ada-002:batch. Because the interface is OpenAI-compatible, existing OpenAI SDKs and clients work with a change of base URL and API key. The model lists no supported parameters beyond what the endpoint itself defines, so you should not expect tuning knobs such as temperature or top_p; embeddings endpoints do not use them. Send your text input and read the embedding vectors from the response.
One practical consideration is that this is described as a legacy model. If you are starting a new project and want the current generation of OpenAI embeddings, check what else api14 offers before committing. For teams already using Ada 002 vectors in production, keeping the same model avoids re-embedding an entire corpus, which is often the deciding factor.
How to call the OpenAI: Text Embedding Ada 002 (batch) API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "openai/text-embedding-ada-002:batch".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.embeddings.create({
"model": "openai/text-embedding-ada-002:batch",
"input": [
"The quick brown fox",
"Lorem ipsum"
]
});
console.log(result.data.map((d) => d.embedding.length));
Specifications
- Context length
- 8,192
- Max output
- 7,372
- Input
- text
- Output
- embeddings
Requests on api14 · last 7 days
OpenAI: Text Embedding Ada 002 (batch): frequently asked questions
- How much does the OpenAI: Text Embedding Ada 002 (batch) API cost?
- OpenAI: Text Embedding Ada 002 (batch) costs Input $0.18 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of OpenAI: Text Embedding Ada 002 (batch)?
- OpenAI: Text Embedding Ada 002 (batch) reads up to 8,192 tokens per request: prompt, history and documents together. It writes up to 7,372 output tokens per response.
- What can OpenAI: Text Embedding Ada 002 (batch) do?
- OpenAI: Text Embedding Ada 002 (batch) accepts text and returns embeddings.
- How do I call OpenAI: Text Embedding Ada 002 (batch) from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "openai/text-embedding-ada-002:batch". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to OpenAI: Text Embedding Ada 002 (batch)?
- Comparable Embeddings models at a similar price: VoyageAI by MongoDB: voyage-4, OpenAI: Text Embedding 3 Large (batch), Perplexity: Embed V1 4B. Each runs through the same API key, so switching is one string.
OpenAI: Text Embedding Ada 002 (batch) community
New topicThis community has no topics yet. Open the first one about OpenAI: Text Embedding Ada 002 (batch).