奥拉玛云模型

Setup

Install Ollama, then sign in for cloud access:

ollama signin

Run a cloud model:

ollama run qwen3.5:cloud "Explain Kubernetes admission control"

Run a local model without consuming cloud usage:

ollama run qwen3.5:9b "Format this JSON"

Quick decision guide

API access

Use a cloud tag through the local Ollama endpoint:

curl --fail-with-body --silent --show-error \
  --connect-timeout 10 \
  --max-time 120 \
  http://localhost:11434/api/chat \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen3.5:cloud",
    "messages": [{"role": "user", "content": "Explain Kubernetes admission control"}],
    "stream": false
  }'

The direct Ollama Cloud API uses the exact model names returned by /api/tags. These names do not use the local :cloud suffix and may include a size tag. Create an API key in your Ollama account, then:

curl --fail-with-body --silent --show-error \
  --connect-timeout 10 \
  --max-time 120 \
  https://ollama.com/api/chat \
  -H "Authorization: Bearer ${OLLAMA_API_KEY}" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-oss:120b",
    "messages": [{"role": "user", "content": "Explain Kubernetes admission control"}],
    "stream": false
  }'

List models currently exposed by the direct cloud API:

curl --fail-with-body --silent --show-error https://ollama.com/api/tags

See the official cloud API documentation for current authentication and tag conventions.

Integrations

Cloud models use the same Ollama interfaces as local models.

Free versus paid guidance

Ollama model pages classify cloud consumption as low, medium, high or extra high usage. These are usage bands, not published plan entitlements.

FAQ