# AI use cases for Freellmapi (tashfeenahmed/freellmapi) Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Use cases: 5 | Page: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/ FreeLLMAPI is a self-hosted router that puts many providers' free LLM tiers behind one OpenAI-compatible /v1 endpoint, with failover and encrypted key storage. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Point an OpenAI SDK app at one free-tier endpoint: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/one-endpoint-for-openai-sdk-apps/ - Run Claude Code against the free model pool: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/run-claude-code-on-free-model-pool/ - Add a local model server beside the free tiers: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/add-local-model-beside-free-tiers/ - Use Codex CLI through the router's responses endpoint: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/use-codex-cli-through-responses-endpoint/ - Run the router from a menu-bar app with no setup: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/desktop-menu-bar-router-no-account/ ## How to point an OpenAI SDK app at one free-tier endpoint with Freellmapi Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Route any OpenAI client library across many free providers through a single local /v1 URL. **Who it is for:** A developer building a prototype or side project who already uses the OpenAI SDK and wants to avoid paying for tokens while experimenting. **The problem:** Each free provider has its own SDK, rate limits, and failure modes, so stacking them by hand means many integrations and manual retries. **The outcome:** The app sends normal OpenAI-style requests to one local endpoint, and the router picks a model and falls over to another provider when one is rate-limited. ### Steps 1. Run `curl -fsSL https://freellmapi.co/install.sh | bash` (Docker required) or follow the local setup in docs/en/install/01-install.md. 2. Open http://localhost:3001, add your provider keys on the Keys page, and reorder the Fallback Chain if you want a preference. 3. Copy the unified API key from the Keys page header. 4. Set your OpenAI client base URL to http://localhost:3001/v1 and use the unified key as the API key. 5. Send a chat request from your app and confirm a normal completion comes back. ### Prompt to paste into your agent ```text In the freellmapi repo (tashfeenahmed/freellmapi), start the router locally and set the OpenAI SDK base URL in to http://localhost:3001/v1 with the unified key from the Keys page. Expected output: a successful chat completion from the app. Verify that the response includes a model name and that the router dashboard shows one request logged. ``` ### Caveat The README describes the project as for personal experimentation only, so do not treat it as production infrastructure. Risk, account pooling: Spreading traffic across several free-tier keys and providers may conflict with each provider's terms, so check those terms before relying on it. Risk, remote script: The one-line installer pipes a remote script into bash, so read the script first, as the README suggests. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/one-endpoint-for-openai-sdk-apps/ ## How to run Claude Code against the free model pool with Freellmapi Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Configure Claude Code to send its requests to the local router instead of a paid Anthropic account. **Who it is for:** A developer who wants to try Claude Code's workflow for coding tasks while keeping token costs at zero during experiments. **The problem:** Claude Code expects an Anthropic-format endpoint, and setting one up by hand across providers is tedious. **The outcome:** Claude Code runs its coding sessions through the router's Anthropic Messages surface, backed by free models that the router selects. ### Steps 1. Start the router with the one-liner install or the local setup in docs/en/install/01-install.md, then add provider keys on the Keys page. 2. Run `npx freellmapi setup-claude --url http://localhost:3001 --api-key` and append your unified key from the Keys page after the flag. 3. Confirm the setup command backed up your existing Claude Code config before it merged the new settings. (inferred, check the README) 4. Open a project directory and start Claude Code. 5. Ask Claude Code a small coding question and check that the router dashboard logs the request. ### Prompt to paste into your agent ```text In the freellmapi repo (tashfeenahmed/freellmapi), run the setup-claude command against http://localhost:3001 with the unified key from the Keys page, then start Claude Code in . Expected output: Claude Code answers a small coding question. Verify that the router dashboard shows the request and that the Claude Code config file was backed up before the merge. ``` ### Caveat Output quality and speed depend on which free models the router selects at the time, so results will vary between sessions. Risk, account pooling: Routing Claude Code traffic across pooled free-tier keys may breach provider terms, so review each provider's rules first. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/run-claude-code-on-free-model-pool/ ## How to add a local model server beside the free tiers with Freellmapi Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Register llama.cpp, LM Studio, vLLM, or Ollama as a custom provider in the same router. **Who it is for:** A developer who runs a local model on their own hardware and wants it to share the same endpoint and fallback chain as cloud free tiers. **The problem:** Local model servers and cloud free tiers each need separate client configuration, so switching between them breaks existing apps. **The outcome:** Local and cloud models sit behind one /v1 endpoint, and the router can fall over between them under the same chain rules. ### Steps 1. Start your local server (llama.cpp, LM Studio, vLLM, or Ollama) and note its OpenAI-compatible base URL. 2. Install the router with `curl -fsSL https://freellmapi.co/install.sh | bash` or the local setup in docs/en/install/01-install.md. 3. On the Keys page, add a custom provider with that base URL and select the chat, embedding, image, or audio models it serves. 4. Reorder the Fallback Chain so the local model sits where you want it. 5. Send one request with the local model name and confirm the response comes from your server. ### Prompt to paste into your agent ```text In the freellmapi repo (tashfeenahmed/freellmapi), add a custom OpenAI-compatible provider pointing at on the Keys page and route one chat request to it. Expected output: a completion generated by the local model. Verify that the router logs the request under the custom provider and not a cloud provider. ``` ### Caveat The README lists llama.cpp, LM Studio, vLLM, and Ollama as examples of custom endpoints, but the exact setup steps for each server are not in the README, so check their docs. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/add-local-model-beside-free-tiers/ ## How to use Codex CLI through the router's responses endpoint with Freellmapi Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Point Codex CLI at the /v1/responses surface so it runs on free-tier models. **Who it is for:** A developer who uses Codex CLI for terminal coding help and wants to test it without a paid model subscription. **The problem:** Codex CLI needs the Responses API surface, which most free-tier wrappers do not offer. **The outcome:** Codex CLI sends its requests to the router's /v1/responses endpoint and gets answers from the free pool. ### Steps 1. Install and start the router, then add provider keys and copy the unified key from the Keys page. 2. Set Codex CLI's base URL to http://localhost:3001/v1 and use the unified key as its API key. 3. Check your Codex CLI config file for the base URL and key fields and update them. (inferred, check the README) 4. Run a short Codex CLI task in a test directory. 5. Check the router dashboard to confirm the request was logged. ### Prompt to paste into your agent ```text In the freellmapi repo (tashfeenahmed/freellmapi), configure Codex CLI in to use http://localhost:3001/v1 with the unified key from the Keys page. Expected output: Codex CLI completes a small task. Verify that the router logs a /v1/responses request. ``` ### Caveat The README names /v1/responses as what Codex CLI needs, but the exact Codex CLI config keys are not documented here, so the config step is inferred. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/use-codex-cli-through-responses-endpoint/ ## How to run the router from a menu-bar app with no setup with Freellmapi Repo: [tashfeenahmed/freellmapi](https://github.com/tashfeenahmed/freellmapi) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Install the desktop app and use the tray popover key with any OpenAI-compatible client. **Who it is for:** A non-developer or casual user on macOS or Windows who wants a local free AI endpoint without Docker or a terminal. **The problem:** Setting up Docker or a Node project is a barrier for people who only want to try AI tools on their own machine. **The outcome:** The router runs from the tray, and the unified key from the popover works in any OpenAI-compatible app. ### Steps 1. Download the macOS .dmg or Windows .exe installer from the Releases page linked in the README. 2. Install the app and open it from the tray or menu bar. 3. Add your provider keys through the app's dashboard, as described in docs/en/install/01-install.md#desktop-app. 4. Copy the unified API key from the tray popover. 5. Paste the key and http://localhost:3001/v1 into any OpenAI-compatible app and send a message. ### Prompt to paste into your agent ```text Install the freellmapi desktop app from the GitHub Releases page for tashfeenahmed/freellmapi, add provider keys, then copy the unified key from the tray popover. Expected output: a successful reply in . Verify that the tray popover shows a request count increase. ``` ### Caveat The README lists macOS 12 or later and Windows installers, and the Linux desktop build is not mentioned, so check the Releases page for your platform. Risk, account pooling: Pooling several free-tier provider keys in one app may conflict with provider terms, so read each provider's rules first. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tashfeenahmed-freellmapi/desktop-menu-bar-router-no-account/