Ollama Cloud

Inference8 modelcontext maks 1M

Catatan dari sumber

Free plan with a starter amount of usage credits for a smaller set of starter models, reset monthly from the sign-up date. 1 concurrent request. OpenAI SDK-compatible via https://ollama.com/v1.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://ollama.com/api",
  apiKey: process.env.OLLAMA_CLOUD_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Halo!" }],
});

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

.env

OLLAMA_CLOUD_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi Ollama Cloud ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi Ollama Cloud.

1.Buka halaman API key Ollama Cloud ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://ollama.com/api di SDK atau HTTP client.

Model tersedia (8+)

deepseek-v4-pro

Modality: text + reasoning
Context: 1.0M
Rate limit: Session/weekly limits (unpublished)

minimax-m3

Modality: text + image + video + reasoning
Context: 512K
Rate limit: Session/weekly limits (unpublished)

Gemma 4 31B IT

gemma-4-31b-it

Modality: vision + reasoning
Context: 262K

Nemotron 3 Nano 30B A3B

nemotron-3-nano-30b-a3b

Modality: reasoning
Context: 262K

Nemotron 3 Super 120B A12B

nemotron-3-super-120b-a12b

Modality: reasoning
Context: 262K

nemotron-3-ultra

Modality: Text
Context: 256K
Output: Model-dependent
Rate limit: 1 concurrent request, monthly starter credits

gpt-oss:120b

Modality: Text
Context: 128K
Output: Model-dependent
Rate limit: 1 concurrent request, monthly starter credits

gpt-oss:20b

Modality: Text
Context: 128K
Output: Model-dependent
Rate limit: 1 concurrent request, monthly starter credits

Model	Modality	Context	Output	Rate limit
deepseek-v4-pro deepseek-v4-pro	text + reasoning	1.0M		Session/weekly limits (unpublished)
minimax-m3 minimax-m3	text + image + video + reasoning	512K		Session/weekly limits (unpublished)
Gemma 4 31B IT gemma-4-31b-it	vision + reasoning	262K
Nemotron 3 Nano 30B A3B nemotron-3-nano-30b-a3b	reasoning	262K
Nemotron 3 Super 120B A12B nemotron-3-super-120b-a12b	reasoning	262K
nemotron-3-ultra nemotron-3-ultra	Text	256K	Model-dependent	1 concurrent request, monthly starter credits
gpt-oss:120b gpt-oss:120b	Text	128K	Model-dependent	1 concurrent request, monthly starter credits
gpt-oss:20b gpt-oss:20b	Text	128K	Model-dependent	1 concurrent request, monthly starter credits

+ other starter models model lainnya — lihat daftar lengkap di sumber.

Model ini di provider lain (8)

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

FAQ

Apakah API Ollama Cloud gratis?

Ya — menurut sumber: "Free plan with a starter amount of usage credits for a smaller set of starter models, reset monthly from the sign-up date. 1 concurrent request. OpenAI SDK-compatible via https://ollama.com/v1." Data dari mnfst/awesome-free-llm-apis, freellm.net, terakhir di-sync 28 Okt 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di Ollama Cloud?

8 model tercantum per 28 Okt 2026, termasuk deepseek-v4-pro, minimax-m3, Gemma 4 31B IT.

Berapa rate limit Ollama Cloud?

Beda-beda per model, contoh: deepseek-v4-pro: Session/weekly limits (unpublished); minimax-m3: Session/weekly limits (unpublished); nemotron-3-ultra: 1 concurrent request, monthly starter credits. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Ollama Cloud?

1M.