Ollama Cloud
Chat-inference op Ollama Cloud. Gehoste open modellen met je eigen Ollama API key. BYOK — bring your own key.
setup_integration or the Dashboard Vault — they're encrypted
with AES-256-GCM and never exposed.
Required Credentials
Get your API key at ollama.com →
Endpoints (2)
Chat with an Ollama Cloud model. Send a messages array and receive one complete response. Streaming is not supported through this proxy: always pass stream=false. Use list-models to see which models your account can reach.
| Field | Type | Required | Description |
|---|---|---|---|
model |
string | ✓ Yes | Cloud model name, e.g. "gemma4". Call list-models for the models your account can reach — do not guess. |
messages |
array | ✓ Yes | Chat history. Example: [{"role": "user", "content": "why is the sky blue?"}]. Roles: system, user, assistant, tool. |
stream |
boolean | ✓ Yes | Must be false. This proxy returns one complete JSON response; a streaming response cannot be read back. |
think |
string | No | Optional reasoning effort for thinking models: "low", "medium", "high" or "max". |
format |
string | No | Optional. "json" for JSON output. A full JSON schema object is supported by Ollama but not yet exposed here. |
options |
object | No | Optional generation settings, e.g. {"temperature": 0.7, "top_p": 0.9, "num_predict": 512}. |
tools |
array | No | Optional function tools the model may call. Tool results come back in message.tool_calls. |
List the Ollama Cloud models available to this API key. Returns model names, sizes and metadata. Call this before chat instead of guessing a model name.
No input parameters required.
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| chat | ollama_chat |
| list-models | ollama_list_models |
Website