Eleven v4 API: settings, cost and integration

Read in Russian

Published: Oct 24, 2026, 3:47 AM UTC · Updated: Oct 24, 2026, 3:47 AM UTC

Exact ID: eleven_v4. Check access for your key using GET /v1/models; a published model does not guarantee access for every account.

Prices and billing units

API429 catalog generated Oct 24, 2026, 5:33 AM UTC. The table shows direct request components; other general catalog metrics are not added here. Display prices are rounded to six decimal places; calculations use exact catalog rates. The calculator below follows the direct audio/speech request contract. Sources checked: Oct 24, 2026.

ElevenAPI: $0.08 per 1,000 characters, excluding taxes, fees and duties. Subscription quotas are accounted for separately. Pricing sources are listed below. Batch, cache and special modes are kept separate from the base comparison.

Speech budget by character count

Specifications and compatibility boundaries

• ElevenLabs: more than 90 languages and a native limit of 10,000 characters per request. This is not an established API429 limit or an audio duration guarantee.
• The native dialogue API recommends up to 2,000 total characters for reliable generation. Its text/voice pairs and constraints cannot be transferred to general audio/speech.
• API429 requires model/input, allows voice/response_format and returns an audio stream. The public contract has no confirmed voice list, default voice or character counting algorithm.

Specification: ElevenLabs, checked Oct 24, 2026. These are not verified effective API429 limits. Check native manufacturer parameters and capabilities separately for the client method.

Published capabilities for this exact ID: chat text_to_speech . A missing field is not evidence of a prohibition, but it does not establish compatibility.

Public model observations

Over the last 24 hours: mean successful response time — 99 s; service error rate — 0%. Data as of Oct 24, 2026, 5:34 AM UTC.

Source: public 24-hour statistics. The mean is neither a median nor a response time guarantee; it is not a quality assessment of the voice.

First request: curl, Python, JavaScript

Set API429_API_KEY on the server and check the exact ID using GET https://gateway.api429.com/v1/models using the same Bearer key. Generation incurs a charge; there are no automatic retries. An uncertain timeout does not prove there was no charge.

Replace YOUR_VOICE_ID in curl with a confirmed voice for your key. Python and JavaScript require API429_VOICE_ID. Do not run the template with an arbitrary voice. curl saves the body to speech.mp3; inspect the response before use.

curl

curl --fail-with-body https://gateway.api429.com/v1/audio/speech \
  -H "Authorization: Bearer $API429_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"eleven_v4","input":"Hello! This is a short speech generation example through API429.","voice":"YOUR_VOICE_ID","response_format":"mp3"}' \
  --output speech.mp3

Python 3

import base64
import json
import os
import urllib.request
from pathlib import Path

key = os.environ["API429_API_KEY"]
base = "https://gateway.api429.com/v1"
headers = {"Authorization": "Bearer " + key, "Content-Type": "application/json"}
model = "eleven_v4"
with urllib.request.urlopen(urllib.request.Request(base + "/models", headers=headers), timeout=30) as response:
    available = {item["id"] for item in json.load(response)["data"]}
if model not in available:
    raise ValueError("Model unavailable to this key")
payload = json.loads("{\"model\":\"eleven_v4\",\"input\":\"Hello! This is a short speech generation example through API429.\",\"voice\":\"YOUR_VOICE_ID\",\"response_format\":\"mp3\"}")
payload["voice"] = os.environ["API429_VOICE_ID"]
if not payload["voice"] or payload["voice"] == "YOUR_VOICE_ID":
    raise ValueError("Set a confirmed voice ID")
request = urllib.request.Request(base + "/audio/speech",
    data=json.dumps(payload).encode("utf-8"), headers=headers, method="POST")
with urllib.request.urlopen(request, timeout=180) as response:
    content_type = response.headers.get("Content-Type", "").split(";")[0].strip().lower()
    if content_type not in ("audio/mpeg", "audio/mp3"):
        raise ValueError("Expected MP3 MIME; inspect response before saving")
    audio = response.read()
if not audio:
    raise ValueError("Empty audio")
Path("speech.mp3").write_bytes(audio)

JavaScript: Node.js 18+

import { writeFile } from "node:fs/promises";
const key = process.env.API429_API_KEY;
if (!key) throw new Error("Set API429_API_KEY");
const base = "https://gateway.api429.com/v1";
const headers = { Authorization: "Bearer " + key, "Content-Type": "application/json" };
const model = "eleven_v4";
const available = await fetch(base + "/models", { headers, signal: AbortSignal.timeout(30000) });
if (!available.ok) throw new Error("Models HTTP " + available.status);
if (!(await available.json()).data.some(item => item.id === model)) throw new Error("Model unavailable to this key");
const payload = {"model":"eleven_v4","input":"Hello! This is a short speech generation example through API429.","voice":"YOUR_VOICE_ID","response_format":"mp3"};
payload.voice = process.env.API429_VOICE_ID;
if (!payload.voice || payload.voice === "YOUR_VOICE_ID") throw new Error("Set a confirmed voice ID");
const response = await fetch(base + "/audio/speech", {
 method: "POST", headers, body: JSON.stringify(payload), signal: AbortSignal.timeout(180000)
});
if (!response.ok) throw new Error("Generation HTTP " + response.status);
if (!["audio/mpeg", "audio/mp3"].includes((response.headers.get("content-type") || "").split(";")[0].trim().toLowerCase())) throw new Error("Expected MP3 MIME");
const bytes = Buffer.from(await response.arrayBuffer());
if (!bytes.length) throw new Error("Empty audio");
await writeFile("speech.mp3", bytes);

The examples are checked offline against the client contract and public schema. No paid execution or result quality is claimed. A verified complete image jobs contract is not available here: asynchronous fields and polling are omitted.

n8n: HTTP Request and saving the result

1. Check access to the exact ID using GET /v1/models.
2. Create an HTTP Request with POST to https://gateway.api429.com/v1/audio/speech; store the Bearer key in credentials.
3. Send the JSON from curl with a confirmed voice. Do not include the key in a workflow export.
4. Choose binary response handling and check the audio MIME and nonempty body.

HTTP Request documentation. Compatibility with specialized AI nodes and native SDKs needs separate verification.

Three options for your own comparison

Compare identical tasks and acceptance criteria. These are speech models, not a quality ranking; conditional rows apply to their own configurations and do not form an equivalent benchmark.

Version and release date

Manufacturer release date, ElevenLabs: Sep 28, 2026. The exact predecessor has not been established in the reviewed sources. This does not automatically replace the ID. The model’s addition date in API429 is unknown.

Frequently asked questions

Sources and review

• elevenlabs.io/docs/overview/models
• elevenlabs.io/blog/eleven-v4
• elevenlabs.io/pricing/api
• elevenlabs.io/docs/api-reference/text-to-dialogue/convert
• gateway.api429.com/api/public/catalog
• gateway.api429.com/api/public/openapi.json
• client.api429.com/documentation

Editorial review: Oct 24, 2026. Pricing · Getting started · Compare the family: ElevenLabs