Sidzedze ƒe gɔmeɖoanyi / Dɔwɔlawo

Nkplɔ̃nuwo, ɖeƒeɖeɖewo kple embeddings

App ƒome tɔ gbɔgbɔɖididiwo, kple ɖeɖe ƒe dɔwɔnuwo: ƒeɖeɖe, fidiowɔ, ɖeɖe, nuŋɔŋlɔ siwo nye nuŋɔŋlɔ, kple embeddingswo, ɖeka ɖeka ƒe dɔwɔnu si woasi ƒe dɔwɔnu ɖe wò wòƒe kaba.

Woɖe axa sia gɔme to mɔ̃ dzi be wòanɔ bɔbɔe. Eŋlisigbe me gbãtɔae nye gɔmeɖeɖe si sɔ.

Ŋwɔna ƒe dɔwɔwɔnawo ƒe ɖeɖefiaɖeɖe

Ŋɔŋlɔ si wòɖo fofonɔ ɖe fofonɔ womanyẽ kple ɖe nuɖuɖu siwo wòɖo woɖa ɖe woɖo wɔwɔna gɔme la. Enye nuɖuɖu siwo wòɖo wowɔ kple... ?image ɖeka ƒe app me.

POST https://nymbot.ai/api/v1/images/generations — ƒe API key ɖe, alo a Lightning payment per request.

Ids ƒoawo ƒo wò le GET /api/v1/models?type=image. Standard ɖeaɖea la, @cf/black-forest-labs/flux-1-schnell, costs a flat 5 standard credits (50 sats) a picture. Every other generator spends Pro credits at its own price, with the usual fee and margin, as in aplikã la. n Xɔ́wɔwɔwo ƒe taƒoƒo n ɣeyi ɖeka ɖe nu si wòkpɔ ɖeka gbɔ. Esia nye mɔ si generator melɔ nu o, wòɖu eɖokui ɖe nu si wòɖo ɖe eŋu o; standard generator la le prompt la ɖe ɖo ko.

resolution eɖe ɖekaɖeka ɖekaɖeka fia eyaɖe xɔxɔe. Viã url, each picture is uploaded to a public Blossom host and you get its link (a few generators only hand back a link of their own, which is passed on). Anyone with the link can open it and it cannot be taken down again; see API la gbɔ ɖe nu kae gbɔna?. Kple b64_json ŋutikpɔkpɔ la ɖoa ɖe eƒe ɖeɖe me eye wònye ɖe ɖi ɖaɖa, eye wònye ɖe ɖi ɖaɖa o. Ŋutikpɔkpɔ le ɖe ɖeɖe me be a data: URL le image_url is checked the same way as an ɖia ɖa eye ɖe Blossom gbãtɔ hã be nye nu si generator la ate ventyConfigɖe ɖe e; ele dze ɖe ɖe le gbãɣã be ne request la le kpeɖeɖe ɖe dze dzesi le nu si wogbeɖe ɖe o la gbã.

Ne dɔ kekeli wòna nu me la n ŋutikpɔkpɔwo va fɔ, wònye wo dome siwo le dɔ wɔm la, wònye wo ƒe dɔwɔnuwo ɖe ɖe wo ɖe (ɖe nya siwo nye eye dɔwɔnuɖinyaɖuɖu la me siwo va fɔ la ɖe nya me la gbãtɔ) eye, ɖe nymbot.failed eɖe nuɖeaɖe wòɖeaɖe le ɖekawo me ɖe. Ne nuɖeaɖeɖe nyaɖeaɖe ɖe, eɖeɖe ɖe ɖe nyaɖeaɖeɖe la me 502.

Gbɔbɔɖeɖe

{
  "created": 1790726400,
  "model": "nano-banana",
  "cost": 0.2126,
  "data": [
    {
      "url": "https://blossom.example/5c0e4b7d3a91f2e8...c4.png",
      "content_type": "image/png"
    }
  ],
  "nymbot": { "balance": "pro", "charged_credits": 1.817, "charged_sats": 181.7, "balance_credits": 410.608, "balance_sats": 41060.8 }
}

cURL

curl https://nymbot.ai/api/v1/images/generations \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana",
    "prompt": "A lighthouse at dusk, oil painting",
    "size": "16:9"
  }'

Python

import os
import requests

res = requests.post(
    "https://nymbot.ai/api/v1/images/generations",
    headers={"Authorization": "Bearer " + os.environ["NYMBOT_API_KEY"]},
    json={"model": "nano-banana", "prompt": "A lighthouse at dusk, oil painting", "size": "16:9"},
)
res.raise_for_status()
print(res.json()["data"][0]["url"])

JavaScript

const res = await fetch("https://nymbot.ai/api/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.NYMBOT_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ model: "nano-banana", prompt: "A lighthouse at dusk, oil painting", size: "16:9" }),
});
const body = await res.json();
console.log(body.data[0].url);

ŋutikpɔkpɔwo ɖaka ɖi

Eɖea ŋutifafa si wòɖo ɖe eŋu ɖe, ɖe fiaɖeɖe si wòɖo ɖe eŋu ɖe. Edzi nye OpenAI ƒe edit endpoint, eye nye OpenAI SDKs ƒe... images.edit eɖoa dɔ ɖeka ɖe. Pro gãɖiɖiwo ko kple edit xɔxɔ nuɖuɖu ƒe ɖekeɖeke ƒe ƒeɖeɖe me ɖe eme.

POST https://nymbot.ai/api/v1/images/edits — ƒe API key ɖe, alo a Lightning payment per request. Ɖeka la nye multipart/form-data, ɖeka ƒe 32 MB ɖo.

The picture you upload is checked to be a well-formed PNG, JPEG, WebP or GIF, sent on as its real type, and put on a public Blossom host, because the generators fetch their input by link. Treat it as public. If the edit fails and nothing is charged, the hosted copy is deleted again. The response has the same shape as for generation. Pricing is the generator's price, which for some generators includes a charge for the input picture.

Gbɔbɔɖeɖe

{
  "created": 1790726460,
  "model": "nano-banana",
  "cost": 0.2126,
  "data": [{ "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..." }],
  "nymbot": { "balance": "pro", "charged_credits": 1.817, "charged_sats": 181.7, "balance_credits": 408.791, "balance_sats": 40879.1 }
}

cURL

curl https://nymbot.ai/api/v1/images/edits \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F model=nano-banana \
  -F image=@photo.png \
  -F prompt="Make it a snowy evening"

Python

import base64, os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("photo.png", "rb") as f:
    result = client.images.edit(model="nano-banana", image=f, prompt="Make it a snowy evening")

with open("edited.png", "wb") as out:
    out.write(base64.b64decode(result.data[0].b64_json))

JavaScript

import fs from "node:fs";
import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const result = await client.images.edit({
  model: "nano-banana",
  image: fs.createReadStream("photo.png"),
  prompt: "Make it a snowy evening",
});
await writeFile("edited.png", Buffer.from(result.data[0].b64_json, "base64"));

Videwo

A video takes minutes, so it runs in the background. You submit it, get an id straight away, and ask about the id until it is done. Every video generator spends the Pro balance.

POST https://nymbot.ai/api/v1/videos — ƒe API key ɖe, alo a Lightning payment per requestDziɖeɖe 202.

ɖokpe siwo le gãawo la le ɖokui me ɖekae ne èɖoa ɖe eŋu, tso generator, resolution kple length ƒe nuɖeɖe me, ɖe èyaɖe eŋu la, wòanya eŋu tso wò Pro balance me beɖe nuɖeɖe si provider la ɖoa ɖe eŋu la, eye wòawɔ nu si nye cost, estimated_cost kple nymbot. If the provider refuses the job, nothing is charged. If the render later fails, or the finished clip cannot be stored and the provider did not bill for it, the charge is refunded once, automatically. A render that is still going after an hour is given up, and keeps its charge, because the provider bills a render once it accepts it. A refund returns the credits but does not lower the key's spend count.

Aɖeɖe (202)

{
  "id": "vid_3e9a51c07b2f4d86e0a1c4f2",
  "object": "video",
  "model": "veo",
  "status": "in_progress",
  "created": 1790726400,
  "seconds": 8,
  "resolution": "1080p",
  "estimated_cost": 3.18,
  "expires_at": 1790812800,
  "cost": 3.18,
  "nymbot": { "balance": "pro", "charged_credits": 31.8, "charged_sats": 3180, "balance_credits": 378.808, "balance_sats": 37880.8 }
}

status starts as in_progress, alo completed video la ƒe ɖe ya la le eme data ɣeɖe gbɔna generator la ɖo ɖeka ɖeɖe be.

Mekpɔ nɔ video ɖeka dzi ɖe nya kpeɖeɖe me

GET https://nymbot.ai/api/v1/videos/{id} — ƒeɖu mɔkpɔkpɔ si nye nym si ɖe ɖe nya la ƒe mɔkpɔkpɔ. Mɔkpɔkpɔ si ɖo eƒe nuɖeɖewo nu la ɔ, nɛ la ɔ le dzesi ɖe ɖe ɖeɖe gɔme hã.

E va ɖe nu 202 ɣe video la ɖeaɖea la kple 200 ɣesia wòɖo ɖo alo eɖu akɔ; ɖo ɖe nu ɖea ɖe ɖe 5 kple 10 dzroɖanɖe. Ŋɔŋlɔ ɖeka ɖeka ɖe nuɖatia ɖe ɖeka eye eɖoa eɖomɔ ɖe ɖeka; eɖea nu ɖe video la gbɔ gake alo; dɔwɔwɔ ɖeka ɖeka kɔ ɖe ɣe 24 megbe be wowɔe. GET /api/v1/videos lɔlɔ̃ si nɔ dɔwɔwɔ wu 50 si nya la yi nye {"object": "list", "data": […]}.

Ɖeɖe (200)

{
  "id": "vid_3e9a51c07b2f4d86e0a1c4f2",
  "object": "video",
  "model": "veo",
  "status": "completed",
  "created": 1790726400,
  "seconds": 8,
  "resolution": "1080p",
  "estimated_cost": 3.18,
  "expires_at": 1790812800,
  "completed_at": 1790726590,
  "data": { "url": "https://blossom.example/9b41d0c2e7a3f658...1e.mp4", "content_type": "video/mp4" },
  "cost": 3.18,
  "nymbot": { "balance": "pro", "charged_credits": 31.8, "charged_sats": 3180 }
}

status e nya in_progress, completed eve failedDɔ si meɖe ɖu... error ({"code": "generation_failed", "message": …}); ɖe ɖu ɖe ɖi, cost 0 kple ƒeɖe ɖe? nymbot lẽawo refunded_credits kple refunded_sats. Video si wòwɔ ɖe la le Blossom host si gbɔkpɔ gbɔ kpɔ ɖe, be ảnhiwo si wòwɔ ɖe nya ɖe.

cURL

curl https://nymbot.ai/api/v1/videos \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "veo", "prompt": "Waves rolling onto a beach at sunrise", "duration": 8, "aspect_ratio": "16:9"}'

curl https://nymbot.ai/api/v1/videos/vid_3e9a51c07b2f4d86 \
  -H "Authorization: Bearer $NYMBOT_API_KEY"

Python

import os, time
import requests

headers = {"Authorization": "Bearer " + os.environ["NYMBOT_API_KEY"]}

job = requests.post(
    "https://nymbot.ai/api/v1/videos",
    headers=headers,
    json={"model": "veo", "prompt": "Waves rolling onto a beach at sunrise", "duration": 8, "aspect_ratio": "16:9"},
).json()

while True:
    time.sleep(8)
    status = requests.get("https://nymbot.ai/api/v1/videos/" + job["id"], headers=headers).json()
    if status["status"] in ("completed", "failed"):
        break

print(status["data"]["url"] if status["status"] == "completed" else status["error"])

JavaScript

const headers = {
  "Authorization": "Bearer " + process.env.NYMBOT_API_KEY,
  "Content-Type": "application/json",
};

const job = await (await fetch("https://nymbot.ai/api/v1/videos", {
  method: "POST",
  headers,
  body: JSON.stringify({ model: "veo", prompt: "Waves rolling onto a beach at sunrise", duration: 8, aspect_ratio: "16:9" }),
})).json();

let status;
do {
  await new Promise((r) => setTimeout(r, 8000));
  status = await (await fetch("https://nymbot.ai/api/v1/videos/" + job.id, { headers })).json();
} while (status.status !== "completed" && status.status !== "failed");

console.log(status.status === "completed" ? status.data.url : status.error);

Takpala ɖe nuŋɔŋlɔ me

Nuŋɔŋlɔwo le ɖe ɖe eye wòana audio ƒe nuŋɔŋlɔla ɖeka, eye menye link ene o. Enye OpenAI ƒe speech endpoint, eye... audio.speech.create OpenAI SDKswo me wòɖo nya.

POST https://nymbot.ai/api/v1/audio/speech — ƒe API key ɖe, alo a Lightning payment per request.

The standard voice costs a flat 3 standard credits (30 sats) a request, as in the app. Aura 2 is Pro, priced by the characters you send. The response body is the audio, with a matching Content-Type; tsea la le ɖe X-Nymbot-Cost-Sats ŋkpɔkpɔɖe. Ne ɖeŋuɖeɖuŋu ƒe model la gblẽ la, menye nu siwo va ɖe gbɔ o.

Gbɔbɔɖeɖe

HTTP/1.1 200 OK
Content-Type: audio/mpeg
X-Nymbot-Cost-Sats: 4.2
X-Nymbot-Balance-Sats: 41055.6

(audio bytes)

cURL

curl https://nymbot.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aura-2", "voice": "luna", "input": "Your invoice has been paid."}' \
  --output speech.mp3

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

audio = client.audio.speech.create(
    model="aura-2",
    voice="luna",
    input="Your invoice has been paid.",
)
audio.write_to_file("speech.mp3")

JavaScript

import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const audio = await client.audio.speech.create({
  model: "aura-2",
  voice: "luna",
  input: "Your invoice has been paid.",
});
await writeFile("speech.mp3", Buffer.from(await audio.arrayBuffer()));

Audio mɔƒoƒowo kple ŋkɔwo

Ŋkɔɖodziɖi ƒe lisi ɖekawo siwo le gbɔɖea me ɖe nu si wòkpɔ ɖe nuŋɔŋlɔɖeɖe alo ɖe dɔwɔnu ƒe nyaɖeɖe ƒe nuŋɔŋlɔ ɖe nu kpɔɖeŋu me gbãtɔ. Aura 2 ƒe ɖeɖeɖe ƒe nyaɖeɖe 41 ƒe ɖeɖeɖewo le eme eye MeloTTS ƒe nuŋɔŋlɔ ƒe gbɔgbɔɖeɖe ƒia nɔ ɖe ɖekawo me.

GET https://nymbot.ai/api/v1/audio/models — no key needed.

GET https://nymbot.ai/api/v1/audio/voices?language=en — no key needed.

ŊɔŊɔ (ŋkɔʋinyadeƒeๆ)

{
  "object": "list",
  "data": [
    { "id": "luna", "name": "Luna", "provider": "deepgram", "model_id": "aura-2", "models": ["aura-2"], "language": "en", "description": "Aura 2 English voice", "gender": "female", "preview_url": null },
    { "id": "en", "name": "MeloTTS English", "provider": "myshell", "model_id": "@cf/myshell-ai/melotts", "models": ["@cf/myshell-ai/melotts", "melotts"], "language": "en", "description": "English (MeloTTS)", "gender": null, "preview_url": null }
  ]
}

Mɔƒumɔ̃wo ɖea ŋutinyawo ɖe asi. {"object": "list", "data": {"tts": […], "stt": […]}}. Ŋɔŋlɔ dzesi ɖeka ɖeka ɖea eƒe nɔnɔme, nuƒometɔ, max_input_chars, response_formats, languages kple default_voice; transcription model la ɖoa e ƒe ŋkɔ bubuwo, max_file_bytes, max_seconds, ɖomɖomewo kple ƒeɖeɖe ɖe min ɖe ɖeke.

cURL

curl https://nymbot.ai/api/v1/audio/models
curl "https://nymbot.ai/api/v1/audio/voices?language=en"

Python

import requests

print(requests.get("https://nymbot.ai/api/v1/audio/models").json())
for voice in requests.get("https://nymbot.ai/api/v1/audio/voices", params={"language": "en"}).json()["data"]:
    print(voice["id"], voice["model_id"])

JavaScript

console.log(await (await fetch("https://nymbot.ai/api/v1/audio/models")).json());
const voices = await (await fetch("https://nymbot.ai/api/v1/audio/voices?language=en")).json();
for (const v of voices.data) console.log(v.id, v.model_id);

Nuŋɔŋlɔ me ɖeɖe

Whisper ɖe nuŋɔŋlɔ ƒe nuɖe ɖe nuŋɔŋlɔ me. Esia nye OpenAI ƒe transcription endpoint, ɖe na audio.transcriptions.create wɔ dɔ.

POST https://nymbot.ai/api/v1/audio/transcriptions — ƒe API key ɖe, alo a Lightning payment per request. Ɖeka la nye multipart/form-data.

For WAV, WebM, MP4 and Ogg files the length is read from the file before anything runs, so a recording over 30 minutes is refused up front (with 3 seconds' grace). A WAV file's length comes from its sample rate, channels and sample size. The length of other formats, such as MP3, cannot be read up front, so they are limited by size: at the lowest bitrate Nymbot assumes, 8 kbps, 30 minutes is 1.8 MB, and a larger file in such a format is refused with 413 audio_too_long megbe nuɖiɖi ɖeka meɖeɖe. Mèɖaɖɔ nuɖiɖiwo gbɔ ɖekaɖeka me ɖe WAV, WebM, MP4 alo Ogg me. Ne Whisper ɖe nuɖiɖiwo be wole ʒi 30 gbɔ oɖe, eɖe ɖe nuɖiɖi sia gbɔ be wole meɖeɖe o le 413 audio_too_long, and since Whisper did run, 30 minutes are charged.

You pay for the length of the audio, rounded up to the second: the longest of the length read from the file, the length Whisper reports, and the least the file's size allows, at Whisper's per-minute price with the usual fee and margin, and at least 0.05 credit a request. It is paid from the standard balance when that can cover the hold, and from Pro otherwise; a 402 ɖoa nu si ɖeka ɖeka ƒe balance la ɖunaɖuna la. Le app la me la, ɖe nu si wogblɔ le nuƒoa me la menye meɖeɖe gɔme o; le API la me la, womana wònye ɣe ɖeka ɖeka ɖe. Ne Whisper gblẽ la, wòade ɣe ɖeka o.

Gbɔbɔɖeɖe

{
  "text": "Your invoice has been paid.",
  "usage": { "type": "duration", "seconds": 3 },
  "nymbot": { "balance": "standard", "charged_credits": 0.05, "charged_sats": 0.5, "balance_credits": 120.35, "balance_sats": 1203.5 }
}

text ɖea tɔŋɔ si ƒo, srt kple vtt ɖe subtitleswo ɖe, kple verbose_json ɖoa nuɖeaɖe, ɖeɖefia, kple ɣeyiɣi ɖeka ɖekawo. Nuɖeaɖe etɔ̃ siwo menye JSON menye, woƒe dɔwɔwɔ ƒe nuɖeaɖe le headers me.

cURL

curl https://nymbot.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F file=@memo.m4a \
  -F model=whisper \
  -F response_format=json

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("memo.m4a", "rb") as f:
    transcript = client.audio.transcriptions.create(model="whisper", file=f)
print(transcript.text)

JavaScript

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const transcript = await client.audio.transcriptions.create({
  model: "whisper",
  file: fs.createReadStream("memo.m4a"),
});
console.log(transcript.text);

Ŋɔŋlɔ siwo ƒo ɖe nuŋɔŋlɔ me ɖo Eglisigbe me ɖeɖe

POST https://nymbot.ai/api/v1/audio/translations — ƒe API key ɖe, alo a Lightning payment per request. Ɖeka la nye multipart/form-data.

Eƒe ɖokpe ɖe nuɖodziɖodzi ƒe dɔwɔwɔ la gbãtɔ, eye nuɖodziɖodzi ƒe dɔwɔwɔ la ƒe dɔwɔwɔwo ɖeka ɖe, si nye... language, ɖemegbe kple ƒe ɖɔ, gake taktakla la va ɖo ɖekui ɖe English dzi ɖeka nu, nuɖeɖe si wòɖo ɖeɖe la nya ɖe. OpenAI SDKs la ɖe nya le eŋu be audio.translations.create.

cURL

curl https://nymbot.ai/api/v1/audio/translations \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F file=@nota.m4a \
  -F model=whisper

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("nota.m4a", "rb") as f:
    translation = client.audio.translations.create(model="whisper", file=f)
print(translation.text)

JavaScript

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const translation = await client.audio.translations.create({
  model: "whisper",
  file: fs.createReadStream("nota.m4a"),
});
console.log(translation.text);

Embeddings

Ŋɔŋlɔwo ɖe vektoƒe me be woanya ɖe nu si wòɖeaɖa ɖe nuɖeɖe, ɖe nuwo ɖe ɖeka me, kple ɖe nu siwo ƒo ɖe ɖeka me. Modeliwo ƒe dɔwɔwɔwo le Cloudflare dzi eye wogbe nu si wònye standard balance la.

POST https://nymbot.ai/api/v1/embeddings — ƒe API key ɖe, alo a Lightning payment per request.

The models list is the source of truth for which are available and what they cost; Google's EmbeddingGemma, with shorter vectors on request, appears there too when the catalog has a price for it. Embeddings are metered per input token, and the 0.05-credit minimum applies to each request, not to each input, so batching many texts into one request is much cheaper than sending them one at a time.

Gbɔbɔɖeɖe

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0213, -0.0487, 0.0112] }
  ],
  "model": "@cf/baai/bge-m3",
  "usage": { "prompt_tokens": 9, "total_tokens": 9 },
  "nymbot": { "balance": "standard", "charged_credits": 0.05, "charged_sats": 0.5, "balance_credits": 1204.35, "balance_sats": 12043.5 }
}

cURL

curl https://nymbot.ai/api/v1/embeddings \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "@cf/baai/bge-m3", "input": ["Lightning invoices expire.", "Invoices on Lightning have a time limit."]}'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

result = client.embeddings.create(
    model="@cf/baai/bge-m3",
    input=["Lightning invoices expire.", "Invoices on Lightning have a time limit."],
)
print(len(result.data), len(result.data[0].embedding))

JavaScript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const result = await client.embeddings.create({
  model: "@cf/baai/bge-m3",
  input: ["Lightning invoices expire.", "Invoices on Lightning have a time limit."],
});
console.log(result.data.length, result.data[0].embedding.length);