Skip to main content
LithosAI exposes the OpenAI Chat Completions API. Agents that support this protocol connect directly; Codex and Claude Code use a local compatibility adapter. Choose your agent below for setup instructions.

​
Choose a model and reasoning effort

Choose the exact model ID from Models. Speed tiers have distinct IDs, such as deepseek-ai/DeepSeek-V4.1-Flash-fast or deepseek-ai/DeepSeek-V4.1-Flash-ultra. To use another model, choose its full ID, such as zai-org/GLM-5.3-Flash. Reasoning effort is a separate setting. Each guide includes the provider configuration and model and effort controls.

​
Before you begin

Install the agent you want to use, create a key on the API Keys page, and confirm the model ID on the Models page. Follow your agent’s guide to save the key in its settings, secret file, or runtime environment. You can keep using your existing editor, CLI, or Gateway.
LithosAI validates tool schemas strictly. An agent that loads an MCP server whose tool parameters are not a JSON Schema object is rejected with invalid 'parameters' schema. Disable that server or correct its schema.

​
Common issues

These apply to every agent guide.

​
Limitations

  • The minimal configuration enables text and tool calls. Turn on image input, reasoning, or other capability flags only when the selected LithosAI model supports them.
  • Set the context window and maximum output from the selected model’s Models page. The configuration examples use the limits from that page. A lower context window makes the agent compact earlier and reduces the cost of each request.
  • Reasoning tokens and the final answer share the output budget. Selecting max effort does not increase that budget. If a response ends with finish_reason: length, increase the output budget within the model’s limit and allow room for the input.
  • Keep your LithosAI API key in the agent’s own settings or an environment variable. Do not commit it to a project repository.

​
Troubleshooting