LLM Providers
Use this page to choose which models power the Zed Agent and other Zed-owned AI features, including Inline Assistant, Git commit generation, thread summaries, and similar model-backed features.
Model access paths do not configure External Agents or Terminal Threads. External Agents and Terminal Threads usually own their own model access, auth, and configuration.
Choose a Model Access Path
| Model access path | Best when | Source of truth |
|---|---|---|
| Use Zed-Hosted Models | You want models billed through Zed | Account & Billing > Zed-Hosted Models |
| Use API Access | You have provider API access, credits, or usage billing | Use API Access |
| Use an Existing Subscription | You already pay for ChatGPT, Claude, Copilot, or another subscription | Use an Existing Subscription |
| Use a Gateway | You route through OpenRouter, Bedrock, Vercel, or a similar platform | Use a Gateway |
| Use a Local Model | You run models locally or self-hosted | Use a Local Model |
Use the setup pages for provider-specific details. See Agents for the difference between the Zed Agent, External Agents, and Terminal Threads.
Edit Prediction
Edit Prediction has its own provider setup under edit_predictions. LLM providers on this page apply to model-backed Zed AI features such as Zed Agent, Inline Assistant, Git commit generation, and thread summaries.
OpenAI-Compatible Providers
OpenAI-compatible provider setup has moved to Use API Access.