OVHcloud AI Endpoints

Inference13 modelcontext maks 262KGratis: 2 RPM/IP

Catatan dari sumber

Free anonymous tier (no API key, no signup): 2 RPM per IP per model. 20+ open-weight models hosted in EU. OpenAI SDK-compatible.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
  apiKey: process.env.OVHCLOUD_AI_ENDPOINTS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "Qwen3-Coder-30B-A3B-Instruct",
  messages: [{ role: "user", content: "Halo!" }],
});

console.log(response.choices[0].message.content);

.env

OVHCLOUD_AI_ENDPOINTS_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi OVHcloud AI Endpoints ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi OVHcloud AI Endpoints.

1.Buka halaman API key OVHcloud AI Endpoints ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 di SDK atau HTTP client.

Model tersedia (13)

Qwen3-Coder-30B-A3B-Instruct

Modality: Text (code)
Context: 262K
Output: ~32K
Rate limit: 2 RPM (anonymous)

Llama-3.1-8B-Instruct

Modality: Text
Context: 131K
Output: ~4K
Rate limit: 2 RPM (anonymous)

Meta-Llama-3_3-70B-Instruct

Modality: Text
Context: 131K
Output: ~4K
Rate limit: 2 RPM (anonymous)

Qwen3-32B

Modality: Text
Context: 131K
Output: ~32K
Rate limit: 2 RPM (anonymous)

Qwen3.5-397B-A17B

Modality: Text
Context: 131K
Output: ~32K
Rate limit: 2 RPM (anonymous)

Qwen3.5-9B

Modality: Text
Context: 131K
Output: ~8K
Rate limit: 2 RPM (anonymous)

Qwen3.6-27B

Modality: Text
Context: 131K
Output: ~32K
Rate limit: 2 RPM (anonymous)

gpt-oss-120b

Modality: Text
Context: 128K
Output: ~32K
Rate limit: 2 RPM (anonymous)

Model	Modality	Context	Output	Rate limit
Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	Text (code)	262K	~32K	2 RPM (anonymous)
Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	Text	131K	~4K	2 RPM (anonymous)
Meta-Llama-3_3-70B-Instruct Meta-Llama-3_3-70B-Instruct	Text	131K	~4K	2 RPM (anonymous)
Qwen3-32B Qwen3-32B	Text	131K	~32K	2 RPM (anonymous)
Qwen3.5-397B-A17B Qwen3.5-397B-A17B	Text	131K	~32K	2 RPM (anonymous)
Qwen3.5-9B Qwen3.5-9B	Text	131K	~8K	2 RPM (anonymous)
Qwen3.6-27B Qwen3.6-27B	Text	131K	~32K	2 RPM (anonymous)
gpt-oss-120b gpt-oss-120b	Text	128K	~32K	2 RPM (anonymous)

Model ini di provider lain (9)

Nama model yang sama juga muncul di provider lain menurut sumber masing-masing — versi/kuantisasi bisa beda.

FAQ

Apakah API OVHcloud AI Endpoints gratis?

Ya — 2 RPM/IP. Data dari mnfst/awesome-free-llm-apis, freellm.net, terakhir di-sync 28 Jul 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di OVHcloud AI Endpoints?

13 model tercantum per 28 Jul 2026, termasuk Qwen3-Coder-30B-A3B-Instruct, Llama-3.1-8B-Instruct, Meta-Llama-3_3-70B-Instruct.

Berapa rate limit OVHcloud AI Endpoints?

Beda-beda per model, contoh: Qwen3-Coder-30B-A3B-Instruct: 2 RPM (anonymous); Llama-3.1-8B-Instruct: 2 RPM (anonymous); Meta-Llama-3_3-70B-Instruct: 2 RPM (anonymous). Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di OVHcloud AI Endpoints?

262K (Qwen3-Coder-30B-A3B-Instruct).