> ## Documentation Index > Fetch the complete documentation index at: https://docs.summerengine.com/llms.txt > Use this file to discover all available pages before exploring further. # Use the Summer API from Claude Code, Codex, Cursor, Hermes and ChatGPT > One step per agent: paste one prompt into Claude Code, Codex, Cursor or Hermes, or add one connector URL in ChatGPT or Claude. You sign in once and choose Allow with a spend limit. Every agent uses the same API and the same Summer sign-in. Coding agents use the `summer` CLI. Chat apps use the Summer MCP. You sign in once, in the browser, and choose **Allow** with a spend limit. ## The one step for coding agents Paste this into **Claude Code, Codex, Cursor, Hermes** or any agent that can run commands: ```text Prompt for your agent wrap theme={null} Use the Summer API for game assets (docs: https://docs.summerengine.com/llms.txt). Run `npx -y summer-engine@latest login` so I can sign in. Then run `npx -y summer-engine@latest api run 3d/default --input '{"kind":"text-to-3d","prompt":"a stylized treasure chest, game prop"}' --download assets` and tell me where the GLB is. ``` The browser opens the Summer sign-in page. You sign in, pick a spend limit and choose **Allow**. The agent makes its first asset. | Agent | Paste the prompt into | | - | - | | Claude Code | the Claude Code chat in your project folder | | Codex | the Codex chat (CLI or app) in your project folder | | Cursor | the Agent chat | | Hermes | the Hermes Agent chat | | Any other agent | its chat | ## The summer CLI ```bash theme={null} npx -y summer-engine@latest login ``` One browser sign-in. It renews itself, so the agent never asks again on this computer. Then every Summer API call is one command: | Command | Does | | - | - | | `summer api models [id] [--capability 3d]` | Lists models with their input and price | | `summer api estimate --input ''` | The price of one job and a quote that holds it for 15 minutes. Free. | | `summer api run --input '' --download [dir]` | Runs the job, follows it and saves each file as `.`. Add `--quote ` to cap the charge. | | `summer api run --batch jobs.jsonl --download [dir]` | Runs up to 500 jobs from a file with one `{"model", "input"}` per line, all or none, and saves every file | | `summer api jobs [--wait] [--download [dir]]` | Reads a job, follows it, or saves its files | | `summer token` | Prints a one-hour token for `curl`: `Authorization: Bearer $(summer token)` | Run them as `npx -y summer-engine@latest api ...`, or as `summer api ...` once the CLI is installed. The output is JSON when piped or with `--json`, and a short summary in a terminal. In Windows PowerShell or cmd, put the input in a file and pass `--input "@input.json"`. The CLI's MCP server has the same calls as tools: `summer_api_models`, `summer_api_estimate`, `summer_api_run`, `summer_api_batch` and `summer_api_job`. `npx -y summer-engine@latest setup --yes` also installs the `summer-api` skill, which teaches the agent this whole flow, and the `summer-router` skill for AI characters in games. ## ChatGPT and Claude Chat apps use the Summer MCP. Add this address as a custom connector and sign in to your Summer account once: ```text theme={null} https://mcp.summerengine.com/mcp ``` Then ask in plain words, for example "Make a low-poly pine tree for my game with the Summer API". The agent finds the Summer API operations (`models.list`, `models.estimate`, `models.run`) with `summer_search` and runs them with `summer_call`. Results go to your Summer library. Step by step for each app: [Summer in ChatGPT and Claude](https://docs.summerengine.com/mcp/chatgpt-and-claude.md). Coding agents can add the same server: Claude Code `claude mcp add --transport http summer-cloud https://mcp.summerengine.com/mcp`, Codex `codex mcp add summer-cloud --url https://mcp.summerengine.com/mcp`. Every app you connect shows in [Settings > Connected agents & apps](https://summerengine.com/settings/connected-apps) with its own spend limit and **Revoke**. See [sign-in and limits](https://docs.summerengine.com/api/sign-in.md). ## What agents should always do * Read models and prices from `summer api models` or `GET /v1/models`, never from memory. * Price a big batch first with `summer api estimate` or `POST /v1/estimate`, and tell the person the total. Then send it as one batch (`summer api run --batch`, `POST /v1/batches`), not job by job. * Treat `queued` as accepted: the job starts in order and its price is held. Never send it again. * Send a new `Idempotency-Key` for each new job and the same one when retrying it. The CLI does this for you. * Save finished files in the project, and keep the asset id to import the asset again. * Keep tokens out of game code, builds and commits. * On `402`, show the person the error message and stop. `no_credits` links where to add credits; `over_limit` links where to raise this app's limit. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.