Create embeddings
Implements POST /v1/embeddings (OpenAI-compatible).
POST /v1/embeddings
| Address | https://api.hanzo.ai/v1/embeddings |
| Method | POST |
| Operation | post_embeddings |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Implements POST /v1/embeddings (OpenAI-compatible).
Body: {"model": "...", "input": "..."|["...", ...], "encoding_format"?, "dimensions"?} It authenticates the caller, resolves the model to its upstream provider via the shared routing table, rewrites the user-facing model name to the upstream id, and proxies the request to the provider's /embeddings endpoint verbatim.
Request
5 fields, body application/json (required).
| Field | In | Type | Required | Description |
|---|---|---|---|---|
dimensions | body | integer | — | |
encoding_format | body | string | — | |
input | body | any | — | |
model | body | string | — | |
user | body | string | — |
Response
| Status | Body | Meaning |
|---|---|---|
200 | openai.EmbeddingResponse | Success. |
401 | — | No credential, or one this service does not accept. |
403 | — | A valid credential that may not do this. |
200 body — 16 fields.
| Field | In | Type | Always | Description |
|---|---|---|---|---|
data | body | openai.Embedding[] | — | |
data[].embedding | body | number[] | — | |
data[].index | body | integer | — | |
data[].object | body | string | — | |
model | body | string | — | |
object | body | string | — | |
usage | body | openai.Usage | — | |
usage.completion_tokens | body | integer | — | |
usage.completion_tokens_details | body | openai.CompletionTokensDetails | — | |
usage.completion_tokens_details.audio_tokens | body | integer | — | |
usage.completion_tokens_details.reasoning_tokens | body | integer | — | |
usage.prompt_tokens | body | integer | — | |
usage.prompt_tokens_details | body | openai.PromptTokensDetails | — | |
usage.prompt_tokens_details.audio_tokens | body | integer | — | |
usage.prompt_tokens_details.cached_tokens | body | integer | — | |
usage.total_tokens | body | integer | — |
Failure carries the platform error shape — see Errors.
Examples
CLI
SDK
HTTP
MCP
hanzo embeddings create.ts
.py
.go
.rs
.java
import { Configuration, AiApi } from 'hanzoai';
const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postEmbeddings({ dimensions: 0, encoding_format: "<encoding_format>" });from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AiApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AiApi(client).post_embeddings(dimensions=0, encoding_format="<encoding_format>")cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)
resp, _, err := client.AiAPI.PostEmbeddings(context.Background()).Execute()
if err != nil {
return err
}use hanzo_client::apis::{configuration::Configuration, ai_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = ai_api::post_embeddings(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AiApi;
ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));
var result = new AiApi(client).postEmbeddings();curl -X POST https://api.hanzo.ai/v1/embeddings \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"dimensions": 0,
"encoding_format": "<encoding_format>"
}'MCP declares no tool for ai — tools/list on https://api.hanzo.ai/v1/mcp names the products it does reach. Use HTTP or an SDK.
Was this page useful?