> ## Documentation Index > Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request. > Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance. > For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code. > The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust. > Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool. > Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md. # Exploring Models > Learn how to browse, compare, and understand the AI models listed on Phaseo. Phaseo tracks a broad open catalog of text, image, audio, video, embedding, and other AI models. Each model page on Phaseo includes detailed technical and commercial information to help you evaluate, compare, and select the right model for your needs. > [!NOTE] > > The catalog is broader than the Gateway. The Models page shows models with an active Gateway route by default. Select a different Gateway Status only when you intentionally want to inspect coming-soon or inactive catalog entries. *** ## What you'll find on a model page Every model on Phaseo contains the following key sections: | Section | Description | | - | - | | **Overview** | Includes provider, release date, model type (chat, code, embedding, image, etc.), and short description. | | **Family** | Easily see related models and their relationships. | | **Timeline** | Visualizes release history and major updates over time. | | **Benchmarks** | Shows performance results across benchmarks, easily compare to nearest models. | | **Availability** | Separates active Gateway routes from coming-soon, inactive, and external provider mappings. | | **Pricing** | Displays detailed pricing in USD, normalized for easy comparison to make it easy to see what the model costs. | | **Gateway** | Direct links and quickstarts when a public Gateway route is available. | | **Performance** | Observational latency, throughput, and success data from routed Gateway requests when enough data is available. | ## Catalog models vs routable models Use these terms consistently: | Term | Meaning | | - | - | | Catalog model | Phaseo tracks metadata for the model. A public route may not exist. | | Routable model | At least one provider route is active on the Phaseo Gateway now. | | External mapping | Phaseo tracks a provider offer that is not executed by the Gateway. | For programmatic discovery, `GET /v1/models` returns only routable models by default. Set `availability=all` to inspect the broader set. *** ## Example model page Here's an example of what a model's data might look like within Phaseo: ![GPT-5 Model Page](https://mintcdn.com/aistats/6VRjfVctM0bPEhiS/images/gemini-3-page.png?fit=max\&auto=format\&n=6VRjfVctM0bPEhiS\&q=85\&s=13b983fd0d150e163b92c768a18a9cef) *** ## Comparing models You can compare models side-by-side on metrics such as performance, pricing, and features. Phaseo automatically highlights differences and ranks models based on various benchmark averages. > [card] [Compare Models](https://phaseo.app/docs/v1/exploring/pricing-performance.md) > > Analyze cost vs performance trade-offs to choose the right model for > your workload. > [card] [View Benchmarks](https://phaseo.app/docs/v1/exploring/benchmarks.md) > > Understand how benchmark scores are gathered and standardized. *** ## Finding models by criteria Use filters and tags across the Phaseo interface to locate models that fit your needs: * **By provider:** "Show all Anthropic models." * **By capability:** "List models supporting JSON structured responses." * **By benchmark:** "Top-10 models on GPQA." * **By pricing:** "Models costing under \$0.01 per 1K tokens." * **By release date:** "Recently released models." Each filter combines seamlessly, letting you discover exactly what you need. *** ## Contributing model updates Because AI evolves rapidly, Phaseo relies on contributors to keep model data accurate. Open a GitHub issue to report a correction, submit missing benchmarks, or request new metadata. Include the model page and official sources; maintainers apply approved updates through the database editor. > [card] [Contribute Model Data](https://phaseo.app/docs/v1/contributing/editing-a-model.md) > > Learn how to report a model correction or request a missing entry. *** ## Next steps Now that you understand how models are structured, you can move on to learn about the **organizations** that build them. > [card] [Explore Organizations](https://phaseo.app/docs/v1/exploring/organisations.md) > > Discover the companies and research groups behind each model. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.