> ## Documentation Index > Fetch the complete documentation index at: https://ona.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Model access > Understand default model access, Codex Agent ChatGPT plan support, and custom token providers. Ona provides model access for agents by default, with no configuration required. This is the recommended setup for most organizations. ## Codex Agent and ChatGPT plans Codex Agent and ChatGPT plan connections are currently supported on Ona Cloud only. On Ona Cloud, Codex Agent can run using the model access available to the organization. Users can also connect their ChatGPT account so Codex model requests use their ChatGPT plan. See [Codex Agent](/ona/agents/codex) for how Codex works in Ona. To use your ChatGPT plan for Codex model requests, see [Connect Codex to ChatGPT](/ona/integrations/configure-codex). ## Custom token providers Custom token providers are available by exception for Enterprise customers. If you have a requirement to use your own token provider, [contact sales](https://ona.com/contact/sales) to discuss. For approved custom provider setups, see the provider-specific guides for [OpenAI BYOK](/ona/agents/llm-providers/openai), [AWS Bedrock Mantle](/ona/agents/llm-providers/bedrock-mantle), [AWS Bedrock](/ona/agents/llm-providers/bedrock), [Google Vertex AI](/ona/agents/llm-providers/google-vertex), and [Anthropic](/ona/agents/llm-providers/anthropic). Configure LLM provider dialog showing AWS Bedrock, AWS Bedrock Mantle, Google Vertex AI, Anthropic, and OpenAI options