Ollama Cloud

The same models and commands as local Ollama, but running on someone else’s GPU.

Ollama Cloud is the same model names and client you already use locally, pointed at someone else’s GPU. ollama run gpt-oss:120b-cloud after ollama signin, or call api.ollama.com/v1 with a key.

Nineteen models on the live list, including DeepSeek V4, MiniMax M3, GLM 5.x and Kimi K3. The free slice is monthly starter credits on the starter models, one concurrent request — session and weekly caps are gone. Switching from local is a host change.

Free models: 19
Max context: 1M
Free tier: Monthly starter credits
Requirement: Email account, no card

Endpoint

Base URLhttps://api.ollama.com/v1

Env varOLLAMA_API_KEY

Rate limitMonthly starter credits, 1 concurrent request

OpenAI-compatible
Native SDK: Ollama SDK
text
image
video
code
vision
reasoning

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.ollama.com/v1',
  apiKey: process.env.OLLAMA_API_KEY
})

const response = await client.chat.completions.create({
  model: 'gpt-oss:20b',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

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

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.ollama.com/v1",
    api_key=os.environ["OLLAMA_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-oss:20b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.ollama.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OLLAMA_API_KEY" \
  -d '{
    "model": "gpt-oss:20b",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

npm install ollama

import { Ollama } from 'ollama'

const ollama = new Ollama({ host: 'https://api.ollama.com' })

const response = await ollama.chat({
  model: 'gpt-oss:20b',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.message.content)

pip install ollama

from ollama import Client

client = Client(host="https://api.ollama.com")

response = client.chat(
    model="gpt-oss:20b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response["message"]["content"])

Worth knowing

Same model names as local Ollama, so you can switch by changing the host alone.
Session and weekly caps are gone; the free slice is monthly starter credits on the starter models.

Models you get for free19

GLM 5.2glm-5.2
Kimi K2.6kimi-k2.6
Kimi K3kimi-k3
DeepSeek V4 Pro 0813deepseek-v4-pro:0813
MiniMax M3minimax-m3
GLM 5.1glm-5.1
GLM 5.3glm-5.3
DeepSeek V4 Flash 0731deepseek-v4-flash:0731
GPT-OSS 20Bgpt-oss:20b
GPT-OSS 120Bgpt-oss:120b
MiniMax M2.7minimax-m2.7
Mistral Large 3 675Bmistral-large-3:675b
Nemotron 3 Supernemotron-3-super
Nemotron 3 Nano 30Bnemotron-3-nano:30b
Gemma 4 31Bgemma4:31b
Qwen 3.5 397Bqwen3.5:397b
Nemotron 3 Ultranemotron-3-ultra
GLM 5.3 Flashglm-5.3-flash
Kimi K2.7 Codekimi-k2.7-code