freellmapi Documentation

File: README.md Copy Chapter

Contents Copy Chapter

• Why this exists
• Supported providers
• Compatible CLIs & coding agents
• How it compares
• Features
• Quick start
• Desktop app
• Works with OpenAI-compatible clients
• Languages
• Premium (live catalog)
• Using the API
• Screenshots
• How it works
• Limitations
• Contributing
• Disclaimer

Guides: Install & deploy · API reference · Clients & coding agents · Prompt compression · Architecture & internals · Documentation index · Contributor guide

Why this exists Copy Chapter

Every serious AI lab now offers a free tier, a few million tokens a month, a few thousand requests a day. On its own each tier is a toy. Stacked together, they add up to roughly 4 billion tokens per month of working inference capacity, across 251 model families / 358 provider endpoints from small-and-fast to reasonably capable.

The problem is that stacking them by hand is painful: twenty-nine different SDKs, twenty-nine different rate limits, twenty-nine places a request can fail. FreeLLMAPI collapses that into one OpenAI-compatible endpoint. Point any OpenAI client library at your local server, and it routes transparently across whichever providers you've added keys for.

And the free-tier landscape shifts weekly: providers launch models, retire them, and change quotas without notice. FreeLLMAPI tracks all of that for you. The router pulls a signed model catalog from freellmapi.co on its own, so your install keeps up without a git pull. See Premium (live catalog) for how fast it keeps up.

Supported providers Copy Chapter

Plus a custom provider — point chat, embedding, image, or audio models at any OpenAI-compatible endpoint (llama.cpp, LM Studio, vLLM, a local Ollama, or a remote gateway) from the Keys page.

The full, always-current list lives at freellmapi.co/models with per-model rate limits, context windows, and free-token budgets.

Compatible CLIs & coding agents Copy Chapter

Most of these configure themselves with one command — npx freellmapi setup-claude, setup-codex, setup-aider, and ten more generators that fetch your live catalog, back up existing config, and never clobber what's already there. Claude Code and Codex also get zero-persistence launchers (freellmapi launch, freellmapi launch-codex) that inject credentials into the child process only. Zed and JetBrains AI connect through the opt-in Ollama emulation; Gemini CLI speaks its native wire on /v1beta.

Per-tool recipes, the setup CLI reference, revocable URL tokens for headerless clients, and the MCP server all live in Clients & coding agents →

How it compares Copy Chapter

Based on public documentation, July 2026 — corrections welcome.

Features Copy Chapter

• Every OpenAI surface — /v1/chat/completions, /v1/responses (what Codex CLI needs), /v1/completions (editor ghost-text autocomplete), /v1/images/generations, /v1/audio/speech, /v1/embeddings, and /v1/models — streaming and non-streaming, from the official SDKs or any OpenAI-compatible client. API reference →
• Anthropic Messages API — /v1/messages speaks Anthropic's wire format over the same router, so Claude Code and the official Anthropic SDKs run against your free pool. Details →
• Native Gemini + Ollama surfaces — Gemini CLI can use /v1beta (generateContent, streaming, token counting, models), while opt-in Ollama emulation serves NDJSON chat/generate, tags, metadata, and embeddings for Zed, JetBrains, and other local-model clients.
• Fusion (multi-model synthesis) — request the virtual fusion model and the router fans your prompt out to a panel of diverse free models in parallel, then a judge model synthesizes one answer from the drafts. Details →
• Image generation & text-to-speech — /v1/images/generations and /v1/audio/speech route across the providers that serve media models, including custom OpenAI-compatible media endpoints.
• Tool calling & structured outputs — OpenAI-style tools round-trip across providers (plain-text tool calls are rescued into real tool_calls), plus response_format, seed, logprobs, penalties, and the rest of the sampling params passed through per provider.
• Smart routing, six strategies — live per-model speed/capability/reliability scores rank your chain; automatic fallover retries the next model on 429/5xx with cooldowns and key rotation. Routing in detail →
• Unified models & profiles — the same model on several providers collapses into one entry with strict in-group failover; named fallback-chain profiles (a coding chain, a vision chain) switch from the dashboard or per request via auto:.
• Per-key rate tracking — RPM/RPD/TPM/TPD counters per (platform, model, key) that learn providers' reported ceilings, so routing always stays under every cap.
• Self-updating model catalog — the router syncs a signed catalog from freellmapi.co twice a day: new models, quota changes, and provider quirk fixes land automatically. Premium →
• Sticky sessions & context handoff — conversations stay on one model for 30 minutes; an optional compact handoff note keeps the thread coherent when a mid-chat switch does happen. Details →
• Prompt compression (opt-in) — a shared, fail-open request pipeline can deduplicate prompts, filter tool output, compact repeated JSON, and trim stale context before cache lookup and routing. Details →
• Encrypted keys, one token out — provider keys are AES-256-GCM encrypted in SQLite and decrypted in-memory per request; your apps only ever see a single unified freellmapi-… bearer token.
• Admin dashboard & analytics — React UI to manage keys, reorder the chain, run a playground, and read p50/p95/TTFT analytics over 24h–90d windows; login-gated, dark/light themes, 60 languages.
• MCP server & interactive docs — agents can introspect usable models, provider health, and routing strategy over /mcp; a dependency-free OpenAPI viewer lives at /v1/docs. Coding agents →
• Ops niceties — opt-in response cache, encrypted DB backups, periodic key health checks, bulk key import/export, declarative startup config. Install & deploy →
• Runs anywhere Node 20+ runs — Windows, macOS, Linux servers, or a small ARM SBC (Raspberry Pi included). ~40 MB RSS at idle behind PM2 / systemd / whatever supervisor you prefer.

The scope is deliberately narrow — see what's not supported yet.

Quick start Copy Chapter

One-liner (Docker required — sets up ~/freellmapi, generates an encryption key, pulls the image, and starts the container):

curl -fsSL https://freellmapi.co/install.sh | bash

Prefer to read before you pipe to bash? The script is here. Re-running it is safe: your .env (and encryption key) is preserved and the container updates to :latest.

Open http://localhost:3001, add your provider keys on the Keys page, reorder the Fallback Chain to taste, and grab your unified API key from the Keys page header. That unified key is what you point your OpenAI SDK at.

On Windows, the easiest path is the desktop .exe installer from Releases (below). On Android, see the experimental Termux guide.

Everything else — Docker Compose, local development, declarative startup config, production builds, LAN access, and backups — is in docs/install.md.

Desktop app Copy Chapter

A native menu-bar app lives in desktop/: the entire router + dashboard running locally from your tray, with a glass popover showing live request stats.

Download from Releases — the macOS .dmg and the Windows .exe installer are attached to every release. No account or password to set up: the only credential you need is the unified API key from the tray popover. Build-from-source steps and where your data lives: docs/install.md.

Works with OpenAI-compatible clients Copy Chapter

Anything that can target an OpenAI-compatible base URL works: set it to http://localhost:3001/v1 with the unified key from the dashboard. Claude Code, Codex CLI, Cline / Roo Code, Continue (including inline autocomplete), Aider, opencode, and Cursor each have a short recipe in docs/clients.md — and the router doubles as an MCP server your agents can introspect mid-session.

The fastest setup is generated from the models available on your live server:

npx freellmapi setup-claude --url http://localhost:3001 --api-key

Every generator supports --dry-run, creates a timestamped backup before changing an existing file, and merges into the user's configuration. Launchers keep credentials out of config files entirely: npx freellmapi launch for Claude Code and npx freellmapi launch-codex for Codex.

FreeLLMAPI is local-first and single-user by design. Your provider keys stay in your SQLite database, encrypted at rest, and requests go from your machine to the upstream providers you enabled.

Languages Copy Chapter

The dashboard ships in 60 languages (the desktop tray menu in 6). The UI
auto-detects your browser/system language on first load and you can switch any
time from ⋯ → Settings; the choice is remembered. Right-to-left languages
(العربية, עברית, فارسی, اردو) flip the whole layout automatically, and only the
active language's dictionary is loaded — the rest never touch your bandwidth.

The full list of locales lives in
client/src/i18n/locale-config.ts.

The original six locales are human-reviewed; the newer ones are machine-
translated and improve as native speakers send corrections — a one-string PR is
a great first contribution.

Translations live in client/src/i18n/locales/ as
flat JSON files. To fix a string, edit the value in the locale's JSON file. To
add a language, copy en.json, translate the values, and register the locale in
client/src/i18n/locale-config.ts (and desktop/src/i18n.ts for the tray
strings); npm test checks every locale for key/placeholder parity — PRs
welcome.

Premium (live catalog) Copy Chapter

The router keeps its model catalog fresh on its own: it pulls a signed catalog
from freellmapi.co twice a day and applies new models,
quota changes, and provider quirk fixes to your local DB. Your own
enable/disable choices and custom providers are never touched, and every
download is verified against a pinned Ed25519 key before it is applied.

The catalog currently tracks 29 providers, 251 model families, 358
provider/model endpoints, and roughly 4 billion tokens per month of listed
free-tier capacity. Browse the full set at
freellmapi.co/models.

Premium keeps that signed catalog live on every router you run. When a provider
launches a strong free model, quietly tightens a quota, or breaks a wire format,
live-feed routers receive the update as soon as we ship it.

Go live at freellmapi.co →

• $19/year or $49 once, lifetime. Stripe checkout; cancel anytime, self-serve.
• One fla_ key covers every router you run: desktop, homelab, Raspberry Pi.
• Activate in the dashboard under Premium; cancel or manage billing
  self-serve at freellmapi.co/manage.
• The router itself stays MIT-licensed and fully free, forever. Premium is only
  the live feed, and it's what funds the daily model testing and catalog
  maintenance that keeps the catalog working.

The catalog server never sees your prompts, completions, or provider keys — the
router stays fully self-hosted either way.

Using the API Copy Chapter

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:3001/v1",
    api_key="freellmapi-your-unified-key",
)

resp = client.chat.completions.create(
    model="auto",  # let the router pick; or "auto:fast", "auto:smart", a profile, or a model id
    messages=[{"role": "user", "content": "Summarise the fall of Rome in one sentence."}],
)
print(resp.choices[0].message.content)
print("Routed via:", resp.headers.get("x-routed-via"))

Streaming, the auto:* routing strategies, tool calling, vision input, Gemini Google Search grounding, embeddings, and the Anthropic Messages surface — with curl and Python examples for each — are all in docs/api.md. Every response carries an X-Routed-Via: /<model> header so you can see which provider actually served it.

Screenshots Copy Chapter

Models Copy Section

Pick a routing strategy and watch the monthly token budget fill across the whole provider fleet. Every model shows live reliability, speed, and intelligence scores — the order below is how requests route right now.

Keys Copy Section

Manage provider credentials and grab the unified API key your apps connect with. Each key shows a status dot and when it was last health-checked.

Playground Copy Section

Send a chat completion through the router and see which provider served it, with the model ID and latency printed right on the message. Attach files by button, drag-and-drop, or paste: images (PNG/JPEG/WebP/GIF) are downscaled in the browser and sent as image content parts to a vision-capable model, and text files (TXT/MD/CSV/JSON/LOG) are inlined into the prompt as fenced blocks.

Analytics Copy Section

Request volume, success rate, tokens in and out, average latency, and per-provider breakdowns over 24h / 7d / 30d / 90d windows.

How it works Copy Chapter

One request in, the best free model out: the router picks the highest-priority model with a healthy key that's under all its rate limits, decrypts the key in memory, and calls the provider — on a 429/5xx it cools that key down and retries the next model in your chain. The component walkthrough, routing internals, and operational details live in docs/architecture.md.

Limitations Copy Chapter

Stacking free tiers has real trade-offs: no frontier models, variable latency, no SLA — and the effective intelligence of the endpoint dips late in the day as top models hit their daily caps, then resets at UTC midnight. Read the honest list in docs/architecture.md#limitations before building anything real on this.

Contributing Copy Chapter

Contributors very welcome! See CONTRIBUTING.md for the dev loop, PR expectations, and the policy on AI/LLM-assisted contributions (short version: welcome, same quality bar as any other PR). Good first PRs:

• Add a provider — copy server/src/providers/openai-compat.ts as a template, wire it into server/src/providers/index.ts, seed its models in server/src/db/index.ts, add a test in server/src/__tests__/providers/.
• Add an endpoint — moderations and other OpenAI-compatible surfaces. The provider base class can grow new methods; adapters declare which they support.
• Improve the router — cost-aware routing (cheapest-healthy-fastest tradeoffs), better latency-weighted priority, regional pinning.
• Dashboard polish — charts on the Analytics page, key rotation UX, batch import of keys from .env.
• Docs — more examples, client library snippets for Go/Rust/etc., a deployment recipe for Docker or Fly.

npm install && npm run dev gets you the server on :3001 and the dashboard on :5173, both with HMR. For a repeatable setup, use ./scripts/dev-bootstrap.sh on Bash or .\scripts\dev-bootstrap.ps1 on PowerShell; each preserves an existing .env. PRs should include a test, keep the existing suite green (npm test), and match the .editorconfig / tsconfig defaults already in the repo. Database migration workflow and the full contributor loop are in CONTRIBUTING.md.

Contributors Copy Section

Disclaimer Copy Chapter

This project is for personal experimentation and learning, not production. Free tiers exist so developers can prototype against them; they aren't a stable, supported inference substrate and shouldn't be treated as one. If you build something real on top of FreeLLMAPI, swap in a paid API before you ship. Your relationship with each upstream provider is governed by the terms you accepted when you created your account — those terms still apply when the traffic is proxied through this project, and you're responsible for complying with them.

How each provider's ToS views a personal, single-user proxy — reviewed provider by provider in May 2026 — is in docs/architecture.md#terms-of-service-review.

License Copy Chapter

MIT

File: client/README.md Copy Chapter

React + TypeScript + Vite

This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.

Currently, two official plugins are available:

• @vitejs/plugin-react uses Oxc
• @vitejs/plugin-react-swc uses SWC

React Compiler Copy Chapter

The React Compiler is not enabled on this template because of its impact on dev & build performances. To add it, see this documentation.

Expanding the ESLint configuration Copy Chapter

If you are developing a production application, we recommend updating the configuration to enable type-aware lint rules:

export default defineConfig([
  globalIgnores(['dist']),
  {
    files: ['**/*.{ts,tsx}'],
    extends: [
      // Other configs...

      // Remove tseslint.configs.recommended and replace with this
      tseslint.configs.recommendedTypeChecked,
      // Alternatively, use this for stricter rules
      tseslint.configs.strictTypeChecked,
      // Optionally, add this for stylistic rules
      tseslint.configs.stylisticTypeChecked,

      // Other configs...
    ],
    languageOptions: {
      parserOptions: {
        project: ['./tsconfig.node.json', './tsconfig.app.json'],
        tsconfigRootDir: import.meta.dirname,
      },
      // other options...
    },
  },
])

You can also install eslint-plugin-react-x and eslint-plugin-react-dom for React-specific lint rules:

// eslint.config.js
import reactX from 'eslint-plugin-react-x'
import reactDom from 'eslint-plugin-react-dom'

export default defineConfig([
  globalIgnores(['dist']),
  {
    files: ['**/*.{ts,tsx}'],
    extends: [
      // Other configs...
      // Enable lint rules for React
      reactX.configs['recommended-typescript'],
      // Enable lint rules for React DOM
      reactDom.configs.recommended,
    ],
    languageOptions: {
      parserOptions: {
        project: ['./tsconfig.node.json', './tsconfig.app.json'],
        tsconfigRootDir: import.meta.dirname,
      },
      // other options...
    },
  },
])

File: desktop/README.md Copy Chapter

FreeLLMAPI Desktop

Lean Electron menu-bar app for freellmapi:
runs the whole router locally on 127.0.0.1:31415, with a dark-glass tray
popover (live 24h request chart, quick stats, copy URL/key) and the full
dashboard in a native-feeling window.

The app lives in the main repo (desktop/) and builds against the server and
client sources in the same checkout — no extra setup, no published binaries:
you build it yourself (a few minutes, commands below).

Prerequisites Copy Chapter

• Node.js 20+
• A native build toolchain for better-sqlite3:
  • macOS — Xcode Command Line Tools (xcode-select --install)
  • Windows — Visual Studio Build Tools ("Desktop development with C++")

Build it yourself Copy Chapter

From the repo root (one-time client build + package):

npm install
npm install --prefix desktop  # install desktop dependencies
npm run desktop:dist          # macOS → desktop/dist-electron/FreeLLMAPI-…-arm64.dmg
npm run desktop:dist:win      # Windows → desktop/dist-electron/FreeLLMAPI-…-x64 installer

Locally built apps don't carry the macOS quarantine attribute or Windows
Mark-of-the-Web, so they launch without Gatekeeper/SmartScreen warnings —
no code signing needed.

The Windows build is config-complete but largely untested — issues and PRs
welcome.

Develop Copy Chapter

cd desktop
npm install
npm run rebuild:native   # better-sqlite3 against Electron's ABI (dev loop only)
npm run dev              # bundle + launch

The dev run serves the repo's own client/dist — build it first
(npm run build -w client from the root) or use npm run desktop:dev from
the root, which does both. FREEAPI_REPO=/path/to/checkout overrides the
client/server source location if you ever need a different one.

UI iteration helpers (dev only): FREEAPI_SHOT=1 npx electron . captures the
popover + dashboard to /tmp and quits; FREEAPI_SHOT=hold pins the popover
open for real-screen captures.

Notes Copy Chapter

• DB + config live in ~/Library/Application Support/FreeLLMAPI/ (macOS) /
  %APPDATA%/FreeLLMAPI/ (Windows).
• The server binds loopback only; default port 31415, scan-up on conflict,
  resolved port persisted.
• Do not run plain npm rebuild here — it rebuilds better-sqlite3 for the
  system Node ABI and breaks the Electron dev loop (npm run rebuild:native
  fixes it). Packaging rebuilds natives itself.

File: docker/README.md Copy Chapter

Docker Guide

Docker Compose is the recommended way to run FreeLLMAPI for personal use. The container serves the Express API and the built React dashboard from one process on port 3001, with SQLite persisted in a named volume.

Prerequisites Copy Chapter

• Docker
• Docker Compose
• OpenSSL for generating ENCRYPTION_KEY

Quick Start Copy Chapter

Create a .env file with a 32-byte encryption key:

ENCRYPTION_KEY="$(openssl rand -hex 32)"
printf "ENCRYPTION_KEY=%s\nPORT=3001\n" "$ENCRYPTION_KEY" > .env

Start the app:

docker compose up -d

Open http://localhost:3001, add provider keys on the Keys page, then use the generated freellmapi-... key with any OpenAI-compatible client.

Example API Call Copy Chapter

curl http://localhost:3001/v1/chat/completions \
  -H "Authorization: Bearer freellmapi-your-unified-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Say hello from FreeLLMAPI."}]
  }'

Operations Copy Chapter

Check status:

docker compose ps

Tail logs:

docker compose logs -f freellmapi

Stop the app:

docker compose down

Update to the latest GHCR image after a release:

docker compose pull
docker compose up -d

Rebuild locally from source:

docker compose up -d --build

Configuration Copy Chapter

The freellmapi-data volume stores SQLite data at /app/server/data. Keep the same volume and ENCRYPTION_KEY when upgrading, otherwise existing encrypted provider keys cannot be decrypted.

Example freellmapi.config.json:

{
  "keys": [
    { "platform": "groq", "key": "gsk_...", "label": "main" }
  ],
  "customProviders": [
    {
      "baseUrl": "http://host.docker.internal:11434/v1",
      "label": "Ollama",
      "models": [
        { "model": "llama3.1:8b", "displayName": "Local Llama", "supportsTools": true }
      ]
    }
  ],
  "routing": { "strategy": "balanced" }
}

Published Image Copy Chapter

Images are published to GitHub Container Registry:

docker pull ghcr.io/tashfeenahmed/freellmapi:latest

The Docker workflow builds pull requests without pushing. After this repository receives the workflow on main, pushes to main and version tags publish images to GHCR automatically.

File: docs/README.md Copy Chapter

English · 简体中文

FreeLLMAPI documentation

The root README is the product overview; the detailed guides live here.

Guides Copy Chapter

• Install & deploy — quick start, Docker Compose, local development, declarative startup config, the Docker image, backups, the desktop app, and where your data lives.
• API reference — chat completions, auto:* routing strategies, streaming, tool calling, vision, Gemini Google Search grounding, embeddings, response headers, and the Anthropic Messages surface.
• Clients & coding agents — OpenAI-compatible clients, recipes for Claude Code / Codex CLI / Cline / Continue / Aider / opencode / Cursor, the MCP server, editor autocomplete, and Context Handoff.
• Prompt compression — request-side modes, safeguards, per-request controls, custom tool-output filters, statistics, and preview APIs.
• Architecture & internals — how the router works, routing and operational details, what's not supported, honest limitations, and the provider Terms-of-Service review.

More Copy Chapter

• Android with Termux — experimental local installation using Node's built-in SQLite driver.
• Docker deployment — container configuration and persistent storage.
• Desktop app — build and package the Electron application.
• Contributor guide — development loop, testing expectations, and contribution policy.
• Database migrations — create, apply, inspect, and roll back schema migrations.

Website assets in this directory Copy Chapter

• index.html — project landing page.
• install.sh — Unix Docker bootstrap script.
• install.ps1 — PowerShell bootstrap script.
• success.html — post-install success page.