Ollama Cloud as a session provider
Workspaces can now connect an Ollama Cloud API key and run AI sessions on its hosted open models, including gpt-oss, Kimi K2.7 Code, DeepSeek V4 Pro and GLM.
Ollama Cloud is now a model provider for AI sessions. Add your Ollama Cloud API key under the workspace's model providers, and sessions can run on the models it hosts.
The launcher offers gpt-oss 120B and 20B, Kimi K2.7 Code, DeepSeek V4 Pro and GLM 5.3. The default is gpt-oss 120B. We tested it end to end with a real key: a plan, build, review and test session completed and produced its change behind the approval gate, like any other session.
Ollama bills by plan, not per token, so sessions on Ollama Cloud show a token count but no per-token cost. We don't invent a price for it. Your spend caps still apply to providers that do charge per token.
See models for every provider sessions support, and sessions for how to start one.