OpenAI compatible

Embeddings

Turns text into vector embeddings for search, clustering, and RAG. OpenAI Embeddings compatible — the official SDKs work unchanged. Billed on input tokens only; embeddings generate no output tokens, and there is no streaming form of this endpoint.

POST/v1/embeddings

Key request parameters

Parameter	Type	Description
`model`	string · Required	Embedding model identifier, e.g. `text-embedding-3-large`
`input`	string \| string[] · Required	Text to embed — one string, or an array for a batch. An empty string, an empty array, or an array containing an empty string is rejected with 400.
`encoding_format`	enum	`float` (default) returns number arrays; `base64` returns an encoded string. Forwarded upstream as-is — the gateway never transcodes vectors, and support varies by upstream.
`dimensions`	integer	Requested vector size; must be greater than 0. Forwarded as-is — an upstream that does not support it returns its native size.
`user`	string	End-user identifier for abuse tracking

Key response parameters

Parameter	Type	Description
`object`	string	Always `list`
`data`	EmbeddingData[]	One entry per input, aligned with the request order
`data[].object`	string	Always `embedding`
`data[].index`	integer	Position of the source input
`data[].embedding`	number[] \| string	Number array with `encoding_format=float`; encoded string with `base64`
`model`	string	Model that produced the vectors
`usage.prompt_tokens`	integer	Input tokens — the billed amount
`usage.total_tokens`	integer	Equal to `prompt_tokens`; the output counters are always 0
`X-HashBid-Cost`	decimal string	Charge for this call (response header, non-streaming requests only); currency in `X-HashBid-Cost-Currency`

Integration examples

Replace the API key and model ID in these examples with your values.

cURL

curl https://hashbidx.ai/v1/embeddings \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": "HashBid turns text into vectors"
  }'

Python

from openai import OpenAI

client = OpenAI(api_key="<YOUR_API_KEY>", base_url="https://hashbidx.ai/v1")

result = client.embeddings.create(
    model="text-embedding-3-large",
    input=["first document", "second document"],
)
for item in result.data:
    print(item.index, len(item.embedding))
print(result.usage.prompt_tokens)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://hashbidx.ai/v1",
});

const result = await client.embeddings.create({
  model: "text-embedding-3-large",
  input: ["first document", "second document"],
});
console.log(result.data.map((item) => item.embedding.length));

body, _ := json.Marshal(map[string]any{
  "model": "text-embedding-3-large",
  "input": []string{"first document", "second document"},
})
req, _ := http.NewRequest("POST",
  "https://hashbidx.ai/v1/embeddings", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer <YOUR_API_KEY>")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)

Rust

let resp = reqwest::Client::new()
    .post("https://hashbidx.ai/v1/embeddings")
    .bearer_auth("<YOUR_API_KEY>")
    .json(&serde_json::json!({
        "model": "text-embedding-3-large",
        "input": ["first document", "second document"],
    }))
    .send().await?;
let body: serde_json::Value = resp.json().await?;

If the response includes X-Request-Id, include it when troubleshooting an issue.

All API endpoints

BUILD WITH HASHBIDX

Find your model. Make your first call.

Models & pricing