# freellmapi | Tashfeen | Knowledge Base | Instagit OpenAI-compatible proxy that stacks the free tiers of 16 LLM providers (~1.7B tokens/month) behind one /v1 endpoint — plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only. GitHub Stars: 11.5k Repository: https://github.com/tashfeenahmed/freellmapi --- ## Articles ### [How to Monitor FreeLLM API Performance: REST Endpoints and Desktop Analytics](/tashfeenahmed/freellmapi/how-to-monitor-freellm-api-performance) Monitor FreeLLM API performance with REST endpoints and desktop analytics. Track latency, token usage, success rates, and cost savings easily. - Tags: performance - Published: 2026-07-02 ### [Best Practices for Using FreeLLM API: Security, Routing & Performance Guide](/tashfeenahmed/freellmapi/what-are-the-best-practices-for-using-freellm-api) Discover best practices for FreeLLM API: secure provider keys with AES-256-GCM, use model auto, and enable sticky sessions for peak performance and reliability. Read our guide now. - Tags: best-practices - Published: 2026-07-02 ### [How to Customize FreeLLMAPI Behavior Using a Config File](/tashfeenahmed/freellmapi/how-to-customize-the-api-behavior-using-the-config-file) Customize FreeLLMAPI behavior with its JSON config file. Control API keys, models, fallbacks, and routing via environment variables for tailored API operations. - Tags: how-to-guide - Published: 2026-07-02 ### [FreeLLM API Usage Examples: Python, Curl, Streaming, and Tool Calling](/tashfeenahmed/freellmapi/are-there-examples-of-freellm-api-usage) Explore FreeLLM API usage examples in Python, Curl, streaming, and tool calling. Discover how to leverage 18 free LLM providers with a single unified key and automatic failover. - Tags: usage-examples - Published: 2026-07-02 ### [How to Run and Configure the Router Service for FreeLLM API](/tashfeenahmed/freellmapi/how-to-run-the-router-service-for-freellm-api) Learn to run the FreeLLM API router service with `setRoutingStrategy` and `setCustomWeights`. Configure settings instantly without restarts with this guide. - Tags: how-to-guide - Published: 2026-07-02 ### [How to Install FreeLLM API: Complete Setup Guide for Docker and Node.js](/tashfeenahmed/freellmapi/how-to-install-freellm-api) Install FreeLLM API quickly with Docker or Node.js. Our guide streamlines setup for production environments. Get started with the fastest Docker one-liner installation. - Tags: how-to-guide - Published: 2026-07-02 ### [What Kind of Models Does FreeLLM API Support? A Complete Guide to Providers and Capabilities](/tashfeenahmed/freellmapi/what-kind-of-models-does-freellm-api-support) Discover the wide range of OpenAI-compatible models FreeLLM API supports from over 20 providers like Google and Groq, automatically using free tiers when available. - Tags: deep-dive - Published: 2026-07-02 ### [FreeLLM API Documentation: Complete Guide to the Self-Hosted LLM Aggregation Proxy](/tashfeenahmed/freellmapi/is-there-a-documentation-for-freellm-api) Explore the FreeLLM API documentation. Get a complete guide to the self-hosted LLM aggregation proxy, including OpenAI-compatible endpoints, integrations, and code examples for Python and curl. - Tags: documentation - Published: 2026-07-02 ### [How to Get Started with FreeLLM API: A Self-Hosted OpenAI-Compatible Proxy](/tashfeenahmed/freellmapi/how-to-get-started-with-freellm-api) Get started with FreeLLM API a self hosted OpenAI compatible proxy Use free LLM tiers seamlessly with automatic routing and fallback handling - Tags: getting-started - Published: 2026-07-02 ### [Dependencies for Running FreeLLM API: A Complete Package Guide](/tashfeenahmed/freellmapi/what-are-the-dependencies-for-running-freellm-api) Discover the essential Node.js dependencies like express, zod, axios, react, vite, tailwindcss, electron, and typescript needed to run the FreeLLM API. Your complete package guide. - Tags: getting-started - Published: 2026-07-02 ### [How to Configure the Router Service in FreeLLM API](/tashfeenahmed/freellmapi/how-do-i-configure-the-router-service-in-freellm-api) Configure the router service in FreeLLM API to select optimal models and API keys with priority fallback chains. Learn configuration strategies like balanced fastest or custom. - Tags: how-to-guide - Published: 2026-07-02 ### [Where to Find the Configuration File for FreeLLM API](/tashfeenahmed/freellmapi/where-can-i-find-the-configuration-file-for-freellm-api) Locate the FreeLLM API configuration file easily. Learn about the FREEAPI_CONFIG_PATH environment variable and its default JSON file path for quick access and customization. - Tags: how-to-guide - Published: 2026-07-02 ### [FreeLLM API Features: OpenAI-Compatible Proxy for Free Tier LLMs](/tashfeenahmed/freellmapi/what-are-the-main-features-of-freellm-api) Explore FreeLLM API features: an open-source, self-hosted OpenAI-compatible proxy for free LLMs. Enjoy intelligent routing, failover, and analytics. - Tags: features - Published: 2026-07-02 ### [How to Integrate FreeLLM API into Your Project: A Complete Self-Hosted Setup Guide](/tashfeenahmed/freellmapi/how-to-integrate-freellm-api-into-my-project) Integrate FreeLLM API into your project with this self-hosted setup guide. Access multiple LLM providers via a single OpenAI compatible endpoint and unified API key. - Tags: how-to-guide - Published: 2026-07-02 ### [What Programming Languages Does FreeLLM API Support?](/tashfeenahmed/freellmapi/what-programming-languages-does-freellm-api-support) Explore programming languages supported by FreeLLM API. Discover seamless integration with JSON locale files in React and Electron clients. - Tags: getting-started - Published: 2026-07-02 ### [LLM Providers Supported by FreeLLMAPI: Complete Integration Guide](/tashfeenahmed/freellmapi/which-llm-providers-are-supported-by-freellmapi) Discover which LLM providers FreeLLMAPI supports including Google Gemini, Groq, and Mistral. Integrate seamlessly with our unified endpoint and access free-tier models. - Tags: api-reference - Published: 2026-07-01 ### [How FreeLLMAPI Implements Key Rotation for Load Distribution in Fusion Panels](/tashfeenahmed/freellmapi/how-does-freellmapi-perform-key-rotation-for-load-distribution) Discover how FreeLLMAPI uses key rotation with skip-sets and cooldowns for efficient load distribution and fallback strategies, ensuring optimal API performance. - Tags: how-to-guide - Published: 2026-07-01 ### [How FreeLLMAPI Tracks RPM, RPD, TPM, and TPD Limits for Rate Limiting](/tashfeenahmed/freellmapi/how-does-freellmapi-track-rpm-rpd-tpm-and-tpd-limits) Discover how FreeLLMAPI tracks RPM, RPD, TPM, and TPD limits using in-memory sliding windows and SQLite persistence for effective request management. - Tags: how-to-guide - Published: 2026-07-01 ### [How to Implement a Custom Provider Adapter for a Non-OpenAI API in FreeLLMAPI](/tashfeenahmed/freellmapi/how-to-implement-a-custom-provider-adapter-for-a-non-openai-api-in-freellmapi) Learn to implement a custom provider adapter for non-OpenAI APIs in FreeLLMAPI. Extend BaseProvider, translate responses, and register your adapter to integrate any LLM. - Tags: how-to-guide - Published: 2026-07-01 ### [How the FreeLLMAPI Router Selects the Best Available LLM Model: Bandit Scoring and Fallback Chains](/tashfeenahmed/freellmapi/how-does-the-freellmapi-router-select-the-best-available-llm-model) Discover how the FreeLLMAPI router picks the best LLM model using bandit scoring and fallback chains for optimal performance and reliability. Maximize your API calls. - Tags: internals - Published: 2026-07-01 ### [Understanding the FreeLLMAPI Request Flow: From Client Call to Provider Response](/tashfeenahmed/freellmapi/what-is-the-request-flow-in-freellmapi-architecture) Explore the 10 stage FreeLLMAPI request flow. Learn how it intelligently routes OpenAI compatible requests to free LLM providers with fallback chains and secure key rotation. - Tags: architecture - Published: 2026-07-01 ### [FreeLLMAPI Authentication Flow: Dashboard vs API Access Explained](/tashfeenahmed/freellmapi/what-is-authentication-flow-for-freellm-api-dashboard-vs-api-access) Understand the FreeLLMAPI authentication flow for dashboard and API access. Learn how to secure your LLM proxy requests with email/password or unified API keys. - Tags: how-to-guide - Published: 2026-06-30 ### [How FreeLLMAPI Catalog Sync Updates Model Information: A Technical Deep Dive](/tashfeenahmed/freellmapi/how-does-freellm-api-catalog-sync-update-model-information) Discover how FreeLLMAPI catalog sync automatically updates model information every 12 hours, ensuring accurate metadata and availability while safeguarding your custom configurations. - Tags: deep-dive - Published: 2026-06-30 ### [Security Considerations for Exposing FreeLLMAPI on a Network](/tashfeenahmed/freellmapi/what-are-security-considerations-for-exposing-freellm-api-on-network) Expose FreeLLMAPI on your network securely. Discover defense-in-depth features like hashed tokens, encrypted keys, rate limiting, and cooldowns for safe LLM gateway access. - Tags: best-practices - Published: 2026-06-30 ### [FreeLLMAPI Routing Scoring Strategies: Bandit, Reliability, and Balanced Presets Explained](/tashfeenahmed/freellmapi/what-scoring-strategies-are-available-for-routing-in-freellm-api) Learn about FreeLLMAPI routing scoring strategies like Bandit, Reliability, and Balanced presets. Optimize your LLM requests with expert configuration. - Tags: deep-dive - Published: 2026-06-30 ### [How FreeLLMAPI Handles HTTP Requests Through Upstream Proxies](/tashfeenahmed/freellmapi/how-does-freellm-api-proxy-handle-http-requests-through-upstream-proxies) Learn how FreeLLMAPI routes HTTP requests through upstream proxies using a lazy-loaded dispatcher. Supports HTTP/HTTPS and SOCKS with per-platform bypass. - Tags: internals - Published: 2026-06-30 ### [How Sticky Sessions Maintain Conversation Continuity in FreeLLMAPI](/tashfeenahmed/freellmapi/how-do-sticky-sessions-maintain-conversation-continuity-in-freellm-api) Learn how FreeLLMAPI uses sticky sessions and a unique session ID header to ensure your conversations remain continuous across stateless requests, restoring previous context effortlessly. - Tags: internals - Published: 2026-06-30 ### [How FreeLLMAPI's Health Checker Validates API Keys: A Complete Technical Guide](/tashfeenahmed/freellmapi/how-does-freellm-apiss-health-checker-determine-if-api-key-is-valid) Learn how FreeLLMAPI validates API keys by decrypting credentials and performing HTTP requests, ensuring healthy keys by checking upstream service status codes and disabling faulty ones. - Tags: how-to-guide - Published: 2026-06-30 ### [How FreeLLMAPI Context Handoff Preserves Conversations When Switching Models](/tashfeenahmed/freellmapi/how-does-context-handoff-feature-work-when-freellm-api-switches-models) Discover how FreeLLMAPI context handoff ensures seamless conversation continuity when switching models. Learn how session summaries maintain your chat history. - Tags: internals - Published: 2026-06-30 ### [How Environment Variables Control FreeLLMAPI Behavior: Complete Configuration Guide](/tashfeenahmed/freellmapi/what-environment-variables-control-freellm-api-behavior) Discover how to control FreeLLMAPI behavior using over 20 environment variables. Configure server binding, encryption, rate limiting, and more with this complete guide. - Tags: how-to-guide - Published: 2026-06-30 ### [How to Configure Custom OpenAI-Compatible Endpoints in FreeLLMAPI: A Complete Guide](/tashfeenahmed/freellmapi/how-to-configure-custom-openai-compatible-endpoints-in-freellm-api) Configure custom OpenAI-compatible endpoints in FreeLLMAPI easily. Follow our guide to send POST requests and integrate your models for seamless use. - Tags: how-to-guide - Published: 2026-06-30 ### [Scoring Algorithms Used by FreeLLMAPI for Model Selection: A Multi-Dimensional Convex System](/tashfeenahmed/freellmapi/what-scoring-algorithms-are-used-by-freellm-api-for-model-selection) Discover FreeLLMAPI's multi-dimensional convex scoring system for model selection. Learn how it combines Bayesian sampling, speed, intelligence, and guardrails into one score. - Tags: deep-dive - Published: 2026-06-30 ### [How the FreeLLMAPI Router Selects Providers for LLM Requests](/tashfeenahmed/freellmapi/how-does-freellm-api-router-select-providers-for-requests) Discover how the FreeLLMAPI router intelligently selects LLM providers. Learn about its deterministic pipeline filtering, multi-axis scoring, and fallback chain for optimal performance and resilience. - Tags: internals - Published: 2026-06-30 ### [Rate Limit Ledger in FreeLLMAPI: How It Tracks and Enforces API Limits](/tashfeenahmed/freellmapi/what-is-the-purpose-of-the-rate-limit-ledger-in-freellmapi) Discover how FreeLLMAPI's Rate Limit Ledger uses an internal SQLite mechanism to track, persist, and enforce API request and token quotas for every key, ensuring fair usage. - Tags: how-to-guide - Published: 2026-06-29 ### [How FreeLLMAPI Handles SSE Streaming for Real-Time LLM Responses](/tashfeenahmed/freellmapi/how-does-freellmapi-handle-sse-streaming-for-responses) Discover how FreeLLMAPI uses SSE streaming for real-time LLM responses. Learn about its lazy header strategy, buffering techniques, and support for tool-call dialect rescue. - Tags: internals - Published: 2026-06-29 ### [FreeLLMAPI API Endpoints: Complete Reference to OpenAI-Compatible and Admin Routes](/tashfeenahmed/freellmapi/what-are-the-different-api-endpoints-exposed-by-freellmapi) Explore FreeLLMAPI API endpoints including OpenAI-compatible routes for inference and admin routes for management. Discover all implemented API routes in the tashfeenahmed/freellmapi repository. - Tags: api-reference - Published: 2026-06-29 ### [How to Add a New LLM Provider to FreeLLMAPI: A Step-by-Step Implementation Guide](/tashfeenahmed/freellmapi/how-do-i-add-a-new-llm-provider-to-freellmapi) Learn how to add a new LLM provider to FreeLLMAPI with this step-by-step guide. Implement, register, seed, and test your new provider for seamless integration. - Tags: how-to-guide - Published: 2026-06-29 ### [How to Debug Routing Failures or Rate Limit Issues in FreeLLMAPI](/tashfeenahmed/freellmapi/how-do-i-debug-routing-failures-or-rate-limit-issues-in-freellmapi) Debug routing failures and rate limit issues in FreeLLMAPI. Use getOrderedFusionChain, getRateLimitStatus, and catch RouteError to diagnose model skips with diagnostic details. - Tags: how-to-guide - Published: 2026-06-29 ### [How FreeLLMAPI Handles API Key Encryption: AES-256-GCM Implementation Explained](/tashfeenahmed/freellmapi/how-is-api-key-encryption-handled-in-freellmapi-and-where-are-they-stored) FreeLLMAPI encrypts API keys with AES-256-GCM using Node.js crypto, storing ciphertext securely in SQLite. Learn how this implementation protects your sensitive data in production. - Tags: deep-dive - Published: 2026-06-29 ### [How Tool Calling Works Across LLM Providers in FreeLLMAPI: A Complete Technical Guide](/tashfeenahmed/freellmapi/how-does-tool-calling-functionality-work-across-different-llm-providers-managed-by-freellmapi) Learn how FreeLLMAPI unifies tool calling across 16+ LLM providers. Explore a technical guide to its OpenAI-compatible endpoint, provider normalization, and standard tool_calls conversion. - Tags: deep-dive - Published: 2026-06-29 ### [How FreeLLMAPI Embeddings Work and Why They Cannot Fail Over Across Different Models](/tashfeenahmed/freellmapi/how-do-embeddings-work-with-freellmapi-and-why-cant-they-failover-across-different-models) Learn how FreeLLMAPI embeddings work and why failover is restricted to the same vector space. Discover how this prevents downstream data corruption. - Tags: deep-dive - Published: 2026-06-29 ### [How to Use the Anthropic Messages API with FreeLLMAPI for Claude Clients](/tashfeenahmed/freellmapi/how-can-i-use-the-anthropic-messages-api-endpoint-with-freellmapi-for-claude-clients) Easily access the Anthropic Messages API with FreeLLMAPI. Connect to Claude via OpenAI-compatible calls, enjoy free-tier providers, streaming, and tool support. - Tags: how-to-guide - Published: 2026-06-29 ### [How FreeLLMAPI Manages Context Handoff When Switching Models Mid-Conversation](/tashfeenahmed/freellmapi/how-does-freellmapi-manage-context-handoff-when-switching-models-mid-conversation) Discover how FreeLLMAPI seamlessly switches models mid-conversation. Learn about its context handoff mechanism and session store for uninterrupted AI interactions. - Tags: how-to-guide - Published: 2026-06-29 ### [What Are Sticky Sessions in FreeLLMAPI and How Do They Improve Conversation Consistency?](/tashfeenahmed/freellmapi/what-are-sticky-sessions-in-freellmapi-and-how-do-they-improve-conversation-consistency) Discover how FreeLLMAPI uses sticky sessions to maintain conversation consistency. Learn about session IDs and in-memory context for stateless LLM dialogues. - Tags: how-to-guide - Published: 2026-06-29 ### [How FreeLLMAPI Handles Rate Limiting at Provider and Proxy Levels](/tashfeenahmed/freellmapi/how-does-freellmapi-handle-rate-limiting-at-both-the-provider-and-proxy-levels) FreeLLMAPI uses a two-tier rate-limiting system with SQLite sliding windows to manage provider quotas and penalize overloaded endpoints, ensuring proxy stability. - Tags: how-to-guide - Published: 2026-06-29 ### [FreeLLMAPI Supported Providers: Complete Guide to 17+ LLM Integrations](/tashfeenahmed/freellmapi/what-llm-providers-are-currently-supported-by-freellmapi) Explore FreeLLMAPI's 17+ supported LLM providers like Gemini, Groq, and OpenRouter. Access free-tier models through a unified OpenAI-compatible API. Get started today. - Tags: getting-started - Published: 2026-06-29 ### [How FreeLLMAPI Implements Automatic Failover for LLM Requests When Providers Hit Rate Limits](/tashfeenahmed/freellmapi/how-does-freellmapi-implement-automatic-failover-for-llm-requests-when-providers-hit-rate-limits) Discover how FreeLLMAPI automatically redirects LLM requests when providers hit rate limits. Seamlessly handles up to 20 provider switches per request for uninterrupted service. - Tags: how-to-guide - Published: 2026-06-29 ### [FreeLLMAPI Routing Strategies: 6 Methods for Intelligent LLM Selection](/tashfeenahmed/freellmapi/what-routing-strategies-are-available-in-freellmapi-for-selecting-llm-models) Explore 6 intelligent LLM routing strategies in FreeLLMAPI like priority, balanced, smartest, fastest, reliable, and custom for optimal model selection based on weighted scoring. - Tags: deep-dive - Published: 2026-06-29 ### [How to Contribute a New LLM Provider to FreeLLMAPI: A Complete Developer's Guide](/tashfeenahmed/freellmapi/contribute-feature-provider) Learn how to contribute a new LLM provider to FreeLLMAPI with this comprehensive developer's guide. Follow simple steps to extend BaseProvider and integrate your LLM easily. - Tags: how-to-guide - Published: 2026-06-28 ### [Security Considerations for Exposing the FreeLLMAPI Proxy: A Complete Guide](/tashfeenahmed/freellmapi/security-considerations-exposing-proxy) Learn security considerations for exposing the FreeLLMAPI proxy. Discover defense-in-depth strategies including authentication, encryption, rate limiting, and data leakage prevention. - Tags: security-guide - Published: 2026-06-28 ### [How to Add Multi-Language Support to the FreeLLMAPI Dashboard](/tashfeenahmed/freellmapi/add-multi-language-support-dashboard) Learn to add multi-language support to the FreeLLMAPI dashboard by creating locale files, registering languages, and synchronizing translations for a seamless user experience. - Tags: how-to-guide - Published: 2026-06-28 ### [How the Catalog Sync Updates Available Models in FreeLLMAPI](/tashfeenahmed/freellmapi/catalog-sync-update-models) Learn how FreeLLMAPI's catalog sync automatically updates model availability every 12 hours, ensuring you always have access to the latest enabled models while respecting your settings. - Tags: how-to-guide - Published: 2026-06-28 ### [How to Set Up the FreeLLMAPI Desktop App: Complete Build Guide](/tashfeenahmed/freellmapi/setup-desktop-app) Learn how to set up the FreeLLMAPI desktop app. Follow our complete build guide to run a local OpenAI-compatible API endpoint easily on your machine. Get started now! - Tags: how-to-guide - Published: 2026-06-28 ### [Which LLM Providers Support Vision or Image Input in FreeLLMAPI?](/tashfeenahmed/freellmapi/providers-support-vision-image-input) Discover which LLM providers support vision or image input in FreeLLMAPI. Learn why only Google Gemini models currently work with images, while others fail. Find out more! - Tags: feature-support - Published: 2026-06-28 ### [How the Responses API Differs from Chat Completions in FreeLLMAPI](/tashfeenahmed/freellmapi/responses-api-vs-chat-completions) Discover how FreeLLMAPI's Responses API, a legacy shim, differs from Chat Completions in request structure, tool handling, image support, and streaming events while sharing core infrastructure. - Tags: deep-dive - Published: 2026-06-28 ### [How to Configure Proxy Settings for the FreeLLMAPI Server](/tashfeenahmed/freellmapi/configure-proxy-settings-server) Configure proxy settings for FreeLLMAPI server using PROXY_URL or the REST API. Learn how to set up HTTP/HTTPS and SOCKS4/5 proxies easily. - Tags: how-to-guide - Published: 2026-06-28 ### [How Unified API Key Authentication Works in FreeLLMAPI: A Technical Deep Dive](/tashfeenahmed/freellmapi/unified-api-key-authentication) Learn how FreeLLMAPI unified API key authentication works. Our technical deep dive explains secure validation for OpenAI and Anthropic style keys against a persistent secret. - Tags: deep-dive - Published: 2026-06-28 ### [How to Run FreeLLMAPI in a Production Environment: Complete Deployment Guide](/tashfeenahmed/freellmapi/run-freellmapi-production) Deploy FreeLLMAPI in production with Docker. Secure credentials with an encryption key and expose the service safely. Get the complete deployment guide. - Tags: how-to-guide - Published: 2026-06-28 ### [How to Troubleshoot 429 Rate Limit Errors in FreeLLMAPI: A Complete Guide](/tashfeenahmed/freellmapi/troubleshoot-429-rate-limit-errors) Troubleshoot 429 rate limit errors in FreeLLMAPI with this guide. Learn to inspect headers, query usage database, and check penalty scores for efficient API use. - Tags: how-to-guide - Published: 2026-06-28 ### [FreeLLMAPI Database Schema and Migrations: Complete Technical Reference](/tashfeenahmed/freellmapi/database-schema-migrations) Explore the FreeLLMAPI database schema and understand how TypeScript migrations ensure reproducible schema evolution. Learn about automatic startup migrations and idempotency. - Tags: api-reference - Published: 2026-06-28 ### [How the Health Checker Determines API Key Status in FreeLLMAPI](/tashfeenahmed/freellmapi/health-checker-api-key-status) Discover how FreeLLMAPI's health checker validates API keys. Learn about the automated process for determining key status and ensuring optimal performance. - Tags: internals - Published: 2026-06-28 ### [How Context Handoff Works When Switching Models Mid-Conversation in FreeLLMAPI](/tashfeenahmed/freellmapi/context-handoff-model-switching) Discover how FreeLLMAPI ensures seamless context handoff when switching models mid-conversation. Maintain continuity and an uninterrupted user experience with our innovative solution. - Tags: internals - Published: 2026-06-28 ### [How to Set Up Custom OpenAI-Compatible Endpoints with FreeLLMAPI](/tashfeenahmed/freellmapi/setup-openai-compatible-endpoints) Easily set up custom OpenAI-compatible endpoints using FreeLLMAPI. Register your models once and interact seamlessly with the OpenAI API for your applications. - Tags: how-to-guide - Published: 2026-06-28 ### [How Embeddings Routing Differs from Chat Routing in FreeLLMAPI](/tashfeenahmed/freellmapi/embeddings-vs-chat-routing) Discover how FreeLLMAPI's embeddings routing differs from chat routing. Learn about adaptive multi-armed bandits versus specific model families and vector space consistency. - Tags: deep-dive - Published: 2026-06-28 ### [How to Use the Anthropic Messages API with Claude Clients in FreeLLMAPI](/tashfeenahmed/freellmapi/use-anthropic-messages-api-claude) Learn how to use the Anthropic Messages API with Claude clients in FreeLLMAPI. This guide shows seamless integration and clear instructions for quick setup. - Tags: how-to-guide - Published: 2026-06-28 ### [How API Key Encryption Works in FreeLLMAPI: AES-256-GCM Implementation Guide](/tashfeenahmed/freellmapi/api-key-encryption-implementation) FreeLLMAPI encrypts API keys with AES-256-GCM using Node.js crypto. Learn how this implementation stores ciphertext, IV, and auth tag in SQLite for secure API key management. - Tags: implementation-guide - Published: 2026-06-28 ### [How to Configure the Fallback Chain Priority for LLM Models in FreeLLMAPI](/tashfeenahmed/freellmapi/configure-fallback-chain-priority) Learn how to configure fallback chain priority for LLM models in FreeLLMAPI. Set model precedence using JSON files or REST API endpoints for optimal performance. - Tags: how-to-guide - Published: 2026-06-28 ### [How Per-Key Rate Limiting Works in FreeLLMAPI: RPM, RPD, TPM, and TPD Explained](/tashfeenahmed/freellmapi/per-key-rate-limiting-explained) Learn how FreeLLMAPI uses per-key rate limiting (RPM RPD TPM TPD) with sliding-window counters and SQLite persistence. Track usage per minute and day for your API keys and models. - Tags: deep-dive - Published: 2026-06-28 ### [How to Add a New LLM Provider to FreeLLMAPI: Complete Implementation Guide](/tashfeenahmed/freellmapi/add-new-llm-provider) Learn to add a new LLM provider to FreeLLMAPI. Follow our guide to extend BaseProvider, register your provider, seed models, and add tests for seamless integration. - Tags: how-to-guide - Published: 2026-06-28 ### [How FreeLLMAPI's Router Selects Models and Handles Automatic Fallback](/tashfeenahmed/freellmapi/router-model-selection-fallback) Discover how FreeLLMAPI's router selects models and handles automatic fallback by dynamically scoring and ranking them based on reliability speed and intelligence for seamless API requests. - Tags: internals - Published: 2026-06-28 ### [How FreeLLMAPI Manages Rate Limit Counter Persistence: A Hybrid SQLite Approach](/tashfeenahmed/freellmapi/how-does-freellmapi-manage-persistence-of-rate-limit-counters) Discover how FreeLLMAPI ensures rate limit counter persistence through a hybrid SQLite and in-memory approach. Learn how it survives restarts without sacrificing speed. - Tags: internals - Published: 2026-06-27 ### [What Is the FreeLLMAPI Base URL for OpenAI‑Compatible Endpoints?](/tashfeenahmed/freellmapi/what-is-base-url-for-freellmapi-as-openai-compatible-endpoint) Find the FreeLLMAPI base URL for OpenAI compatible endpoints at https://api.freellmapi.com/v1. Integrate seamlessly with your existing OpenAI tools and applications. - Tags: api-reference - Published: 2026-06-27 ### [How to Use ENCRYPTION_KEY with FreeLLMAPI: Complete Configuration Guide](/tashfeenahmed/freellmapi/how-can-i-use-encryption-key-with-freellmapi) Learn to use ENCRYPTION_KEY with FreeLLMAPI for secure API key storage. This guide details configuration for production and development environments to protect your sensitive data. - Tags: how-to-guide - Published: 2026-06-27 ### [FreeLLMAPI Anthropic Endpoint: Complete Claude Compatibility Implementation](/tashfeenahmed/freellmapi/what-endpoint-does-freellmapi-provide-for-anthropic-claude-compatibility) Discover the Anthropic endpoint FreeLLMAPI offers for seamless Claude client integration. Connect easily using standard SDKs with the `POST /v1/messages` endpoint. - Tags: api-reference - Published: 2026-06-27 ### [How to Use FreeLLMAPI with the OpenAI Python Client: Complete Integration Guide](/tashfeenahmed/freellmapi/how-to-use-freellmapi-with-openai-python-client) Easily integrate FreeLLMAPI with the OpenAI Python client. Set your FreeLLMAPI endpoint and key to access models seamlessly using the official SDK. - Tags: how-to-guide - Published: 2026-06-27 ### [What Is FREELLMAPI_CONTEXT_HANDOFF? Context Preservation Across Model Switches in FreeLLM](/tashfeenahmed/freellmapi/what-is-purpose-freellmapi-context-handoff-feature) Discover FREELLMAPI_CONTEXT_HANDOFF, a feature preserving conversation context between LLM model switches. Learn how it simplifies multi-model interactions. - Tags: feature-explanation - Published: 2026-06-27 ### [How FreeLLMAPI Handles Tool Calling Across Different LLM Providers](/tashfeenahmed/freellmapi/how-is-tool-calling-handled-by-freellmapi-across-providers) Discover how FreeLLMAPI unifies tool calling across diverse LLM providers with Zod validation and a rescue layer, simplifying cross-provider integration. - Tags: how-to-guide - Published: 2026-06-27 ### [How FreeLLMAPI Supports Streaming Responses: An OpenAI-Compatible SSE Implementation](/tashfeenahmed/freellmapi/how-does-freellmapi-support-streaming-responses) Discover how FreeLLMAPI enables streaming responses with its OpenAI-compatible SSE endpoint. Learn how it processes AsyncGenerator chunks for efficient, real-time data delivery. - Tags: internals - Published: 2026-06-27 ### [What Is the Health Checking Service in FreeLLMAPI?](/tashfeenahmed/freellmapi/what-is-purpose-health-checking-service-freellmapi) Discover the FreeLLMAPI health checking service. It validates API keys every 5 minutes, updates their status, and disables invalid keys to ensure secure LLM requests. - Tags: how-to-guide - Published: 2026-06-27 ### [File Path for the Main Proxy Route Handlers in FreeLLMAPI: Complete Server Architecture Guide](/tashfeenahmed/freellmapi/file-path-main-proxy-route-handlers-freellmapi) Find the main proxy route handlers file path at server/src/routes/proxy.ts in FreeLLMAPI. Explore authentication, logging, and request forwarding in this server architecture guide. - Tags: architecture - Published: 2026-06-27 ### [Which LLM Providers Are Built Into FreeLLMAPI? Complete 2025 Provider List](/tashfeenahmed/freellmapi/which-llm-providers-are-built-into-freellmapi) Discover LLM providers in FreeLLMAPI. Access 17 major LLMs like Gemini, Groq, Mistral via one OpenAI compatible endpoint. Explore the complete 2025 list for free tier access. - Tags: getting-started - Published: 2026-06-27 ### [FreeLLMAPI Environment Variable for API Key Encryption: ENCRYPTION_KEY Setup Guide](/tashfeenahmed/freellmapi/what-environment-variable-is-required-for-api-key-encryption) Learn how to set up the ENCRYPTION_KEY environment variable for FreeLLMAPI to securely encrypt your provider API keys at runtime. Follow our simple setup guide. - Tags: how-to-guide - Published: 2026-06-27 ### [How FreeLLMAPI Stores and Encrypts Provider API Keys](/tashfeenahmed/freellmapi/where-are-provider-api-keys-stored-and-how-are-they-encrypted) Discover how FreeLLMAPI secures provider API keys using AES-256-GCM encryption in a SQLite database. Learn about encryption at rest and in-memory decryption for secure API access. - Tags: internals - Published: 2026-06-27 ### [How FreeLLMAPI Handles Rate Limiting Across Different LLM Providers](/tashfeenahmed/freellmapi/how-does-freellmapi-handle-rate-limiting-for-llm-providers) FreeLLMAPI uses sliding-window counters daily caps and cooldowns to manage rate limiting across LLM providers ensuring reliable routing without exceeding quotas. - Tags: how-to-guide - Published: 2026-06-27 ### [What Is the Default Port for the FreeLLMAPI Proxy Server?](/tashfeenahmed/freellmapi/what-is-the-default-port-for-freellmapi-proxy-server) Discover the default port for the FreeLLMAPI proxy server. Learn how to configure it and ensure smooth API communication. Get the essential details now. - Tags: faq - Published: 2026-06-27 ### [How to Set Up FreeLLMAPI Locally Using Docker: A Complete Guide](/tashfeenahmed/freellmapi/how-to-set-up-freellmapi-locally-using-docker) Set up FreeLLMAPI locally with Docker. Follow this guide to generate an encryption key, configure your .env file, and launch the OpenAI-compatible proxy server. - Tags: how-to-guide - Published: 2026-06-27 ### [How to Use FreeLLMAPI for Local Development: Complete Setup Guide](/tashfeenahmed/freellmapi/how-to-use-freellmapi-for-local-development) Learn how to use FreeLLMAPI for local development. This guide shows you how to set up this OpenAI-compatible proxy to aggregate free LLM tiers on your local machine. - Tags: how-to-guide - Published: 2026-06-26 ### [FreeLLMAPI Unified API Key Format: Structure, Generation, and Usage](/tashfeenahmed/freellmapi/what-is-the-unified-api-key-format-for-freellmapi) Learn the unified API key format for FreeLLMAPI. Discover how to structure, generate, and use your freellmapi-<48-hex-characters> key for seamless authentication. - Tags: api-reference - Published: 2026-06-26 ### [Sticky Sessions Duration in FreeLLMAPI: How Long They Last and How They Work](/tashfeenahmed/freellmapi/what-is-the-duration-of-sticky-sessions-in-freellmapi) Discover sticky session duration in FreeLLMAPI. Learn how FreeLLMAPI maintains sessions for 30 minutes and understand context expiration for optimized API usage. - Tags: deep-dive - Published: 2026-06-26 ### [How FreeLLMAPI Handles Sticky Sessions for Conversations](/tashfeenahmed/freellmapi/how-does-freellmapi-handle-sticky-sessions-for-conversations) Discover how FreeLLMAPI ensures conversation continuity with sticky sessions. Learn how UUIDs and the x-llmapi-session-id header maintain context across stateless requests. - Tags: internals - Published: 2026-06-26 ### [How FreeLLMAPI Implements Automatic Failover for Providers: A Technical Deep Dive](/tashfeenahmed/freellmapi/how-does-freellmapi-implement-automatic-failover-for-providers) Learn how FreeLLMAPI ensures constant LLM access with automatic failover. Discover how provider health metrics dynamically reorder the fallback chain for reliable request delivery. - Tags: deep-dive - Published: 2026-06-26 ### [What Information Is Stored in the FreeLLMAPI SQLite Database?](/tashfeenahmed/freellmapi/what-information-is-stored-in-the-freellmapi-sqlite-database) Discover what the FreeLLMAPI SQLite database stores: model catalogs, encrypted API keys, request logs, rate limits, and user sessions. Understand your API's runtime state. - Tags: internals - Published: 2026-06-26 ### [What Database Does FreeLLMAPI Use for Persistence?](/tashfeenahmed/freellmapi/what-database-does-freellmapi-use-for-persistence) Discover why FreeLLMAPI uses an embedded SQLite database for persistence. Learn how it stores rate-limit counters, key status, and request analytics efficiently. - Tags: internals - Published: 2026-06-26 ### [Data Flow for a Client Request in FreeLLMAPI: End-to-End Architecture](/tashfeenahmed/freellmapi/what-is-the-data-flow-for-a-client-request-in-freellmapi) Understand the end-to-end client request data flow in FreeLLMAPI. Explore Express middleware, API key auth, Zod validation, model routing, rate limits, and streaming responses. - Tags: architecture - Published: 2026-06-26 ### [How to Add a New Provider Adapter to FreeLLMAPI](/tashfeenahmed/freellmapi/how-to-add-a-new-provider-adapter-to-freellmapi) Easily add a new provider adapter to FreeLLMAPI by extending existing classes and registering your implementation. Learn the simple steps to integrate custom or OpenAI-compatible APIs. - Tags: how-to-guide - Published: 2026-06-26 ### [Provider Key Statuses in the Health Checker: A Complete Guide to FreeLLMAPI Key Monitoring](/tashfeenahmed/freellmapi/what-are-the-different-statuses-a-provider-key-can-have-in-the-health-checker) Understand FreeLLMAPI provider key statuses: healthy, invalid, error, rate_limited, and unknown. Monitor your API keys effectively with this complete guide. - Tags: deep-dive - Published: 2026-06-26 ### [How FreeLLMAPI Handles Rate Limiting for LLM Providers: A Technical Deep Dive](/tashfeenahmed/freellmapi/how-does-freellmapi-handle-rate-limiting-for-providers) Discover how FreeLLMAPI manages rate limiting across LLM providers with per key, per model, and provider-wide caps for reliable request routing. Learn about sliding windows and exponential backoff. - Tags: deep-dive - Published: 2026-06-26 ### [What Is the FreeLLMAPI Router Service? Core Responsibilities and Architecture](/tashfeenahmed/freellmapi/what-is-the-freellmapi-router-service-responsible-for) Discover the FreeLLMAPI Router Service, the intelligent traffic controller. Learn about its core responsibilities in selecting models, managing quotas, and providing a unified API. - Tags: architecture - Published: 2026-06-26 ### [How API Keys Are Encrypted in FreeLLMAPI: AES-256-GCM Implementation](/tashfeenahmed/freellmapi/how-are-api-keys-encrypted-in-freellmapi) FreeLLMAPI encrypts API keys with AES-256-GCM using Node.js crypto. Learn how we protect your data with this secure implementation stored in SQLite. - Tags: how-to-guide - Published: 2026-06-26 ### [What is the Default Port for the FreeLLMAPI Server?](/tashfeenahmed/freellmapi/what-is-the-default-port-for-the-freellmapi-server) Discover the default port for the FreeLLMAPI server. Learn how to access this powerful tool and avoid common configuration issues. Find out the default port is 3001. - Tags: how-to-guide - Published: 2026-06-26 ### [How to Set Up FreeLLMAPI with Docker: Complete Self-Hosting Guide](/tashfeenahmed/freellmapi/how-to-set-up-freellmapi-with-docker) Learn how to set up FreeLLMAPI with Docker for a self-hosted OpenAI-compatible API. Get intelligent request routing and a React dashboard in minutes. - Tags: how-to-guide - Published: 2026-06-26 ### [How FreeLLMAPI Handles Database Migrations with better-sqlite3 for Schema Updates](/tashfeenahmed/freellmapi/how-are-database-migrations-handled-using-better-sqlite3-for-schema-updates-in-freellmapi) FreeLLMAPI uses better-sqlite3 for efficient, idempotent database migrations ensuring schema consistency. Learn how FreeLLMAPI handles schema updates on server startup. - Tags: how-to-guide - Published: 2026-06-25 ### [Data Retention Period for Request Analytics in FreeLLMAPI: Configuration and Defaults](/tashfeenahmed/freellmapi/what-is-the-data-retention-period-for-request-analytics-in-freellmapi-and-what-controls-it) Configure the request analytics data retention period for FreeLLMAPI. Learn the default 90-day setting and how to adjust or disable it with the REQUEST_ANALYTICS_RETENTION_DAYS variable. - Tags: how-to-guide - Published: 2026-06-25 ### [How FreeLLMAPI Handles Error Redaction and Classification to Sanitize Provider Responses](/tashfeenahmed/freellmapi/what-is-the-process-for-error-redaction-and-classification-in-freellmapi-to-sanitize-provider-responses) Learn how FreeLLMAPI’s error redaction and classification process sanitizes provider responses, preventing sensitive data leaks and identifying retryable or payment-related failures. - Tags: internals - Published: 2026-06-25 ### [How FreeLLMAPI Infers Provider Quota Pool Keys and Manages Shared Quota Tracking](/tashfeenahmed/freellmapi/how-does-the-freellmapi-provider-quota-system-infer-pool-keys-and-manage-shared-quota-tracking) Discover how FreeLLMAPI infers provider quota pool keys and manages shared quota tracking for seamless API key management within your account or project. - Tags: internals - Published: 2026-06-25 ### [How to Integrate Custom OpenAI-Compatible Endpoints with FreeLLMAPI](/tashfeenahmed/freellmapi/how-can-developers-integrate-custom-openai-compatible-endpoints-with-freellmapi) Integrate custom OpenAI compatible endpoints like llama.cpp and LM Studio with FreeLLMAPI. Register local services easily using the POST /custom endpoint for seamless API access. - Tags: how-to-guide - Published: 2026-06-25 ### [How FreeLLMAPI Implements the Anthropic Messages API for Claude Code Compatibility](/tashfeenahmed/freellmapi/how-does-freellmapi-implement-the-anthropic-messages-api-for-claude-code-compatibility) FreeLLMAPI provides Anthropic Messages API compatibility for Claude. Learn how it translates requests, routes them through a unified pipeline, and maps responses for seamless integration. - Tags: how-to-guide - Published: 2026-06-25 ### [Why FreeLLMAPI Uses Family-Based Failover for Embeddings and Avoids Cross-Model Routing](/tashfeenahmed/freellmapi/why-does-freellmapi-use-family-based-failover-for-embeddings-and-avoid-cross-model-routing) FreeLLMAPI uses family-based failover for embeddings, avoiding cross-model routing to ensure vector compatibility for downstream vector stores and similarity searches. - Tags: architecture - Published: 2026-06-25 ### [How FreeLLMAPI Sticky Sessions Maintain Model Consistency in Conversations](/tashfeenahmed/freellmapi/what-are-the-details-of-freellmapis-sticky-sessions-for-maintaining-model-consistency-in-conversations) Discover how FreeLLMAPI sticky sessions leverage an in-memory cache to ensure consistent LLM model responses in multi-turn conversations, expiring after 30 minutes. - Tags: deep-dive - Published: 2026-06-25 ### [How FreeLLMAPI Implements Context Handoff When Switching Models Mid-Session](/tashfeenahmed/freellmapi/how-does-freellmapi-implement-context-handoff-for-conversations-switching-models-mid-session) Learn how FreeLLMAPI enables seamless context handoff mid-conversation. Discover its session cache and system message technique for continuous model switching. - Tags: internals - Published: 2026-06-25 ### [How FreeLLMAPI Encrypts API Keys at Rest with AES-256-GCM and Decrypts Them for Requests](/tashfeenahmed/freellmapi/how-are-api-keys-encrypted-at-rest-and-decrypted-for-requests-in-freellmapi) FreeLLMAPI secures API keys with AES-256-GCM encryption at rest and decrypts them for requests. Discover how FreeLLMAPI protects your credentials using a master secret and SQLite. - Tags: how-to-guide - Published: 2026-06-25 ### [Understanding the Dual Authentication System in FreeLLMAPI: Dashboard vs. Unified API Key](/tashfeenahmed/freellmapi/explain-the-dual-authentication-system-in-freellmapi-dashboard-vs-unified-api-key) Explore FreeLLMAPI's dual authentication: dashboard logins for human operators and unified API keys for automated client requests. Secure your LLM access efficiently. - Tags: deep-dive - Published: 2026-06-25 ### [How FreeLLMAPI Implements Per-Key Rate Limit Tracking (RPM, RPD, TPM, TPD) and Cooldown Management](/tashfeenahmed/freellmapi/what-is-the-mechanism-for-per-key-rate-limit-tracking-and-cooldown-management-in-freellmapi) Discover how FreeLLMAPI tracks per-key rate limits (RPM, RPD, TPM, TPD) and manages cooldowns using a hybrid in-memory and SQLite approach. Prevent provider throttling effectively. - Tags: internals - Published: 2026-06-25 ### [How to Secure FreeLLMAPI When Exposing It on a Network](/tashfeenahmed/freellmapi/secure-freellmapi-exposing-on-network) Learn how to secure FreeLLMAPI on your network. Implement AES-256-GCM encryption, localhost binding, bcrypt authentication, and TLS termination to protect your API. - Tags: how-to-guide - Published: 2026-06-24 ### [What Happens When All Providers in the FreeLLMAPI Fallback Chain Fail?](/tashfeenahmed/freellmapi/what-happens-when-fallback-chain-fails-freellmapi) Learn what happens when all providers in the FreeLLMAPI fallback chain fail. Discover router responses, error codes, and how to handle these failures effectively. - Tags: internals - Published: 2026-06-24 ### [How to Configure Proxy Settings for Outbound Requests in FreeLLMAPI](/tashfeenahmed/freellmapi/configure-proxy-settings-outbound-requests-freellmapi) Configure proxy settings for outbound requests in FreeLLMAPI. Use environment variables or REST API calls for HTTP, HTTPS, and SOCKS5 protocols without restarts. - Tags: how-to-guide - Published: 2026-06-24 ### [FreeLLMAPI Premium Live Catalog: Real-Time Model Updates Explained](/tashfeenahmed/freellmapi/freellmapi-premium-live-catalog-worth-it) Discover FreeLLMAPI's Premium Live Catalog for real-time model updates. Get fresh free-tier models and updated quotas every 12 hours. Unlock continuous value with a license key. - Tags: feature-explanation - Published: 2026-06-24 ### [Embeddings Routing vs Chat Routing in FreeLLMAPI: Architectural Differences Explained](/tashfeenahmed/freellmapi/freellmapi-embeddings-vs-chat-routing) Understand the core architectural differences between embeddings routing and chat routing in FreeLLMAPI. Learn how each method handles model selection and consistency for optimal performance. - Tags: architecture - Published: 2026-06-24 ### [How to Troubleshoot 429 Rate Limit Errors in FreeLLMAPI: A Complete Guide](/tashfeenahmed/freellmapi/troubleshoot-429-rate-limit-errors-freellmapi) Troubleshoot 429 rate limit errors in FreeLLMAPI effortlessly. Learn how to diagnose bottlenecks using response headers and the SQLite usage database. Optimize your API calls today. - Tags: how-to-guide - Published: 2026-06-24 ### [FreeLLMAPI Limitations in Production: 8 Critical Constraints Explained](/tashfeenahmed/freellmapi/freellmapi-production-limitations) Discover FreeLLMAPI limitations for production. Explore 8 critical constraints including quota exhaustion, variable latency, and absent SLA guarantees. Learn why it's unsuitable for production workloads. - Tags: deep-dive - Published: 2026-06-24 ### [How to Monitor Usage Analytics and Request Logs in FreeLLMAPI](/tashfeenahmed/freellmapi/monitor-usage-analytics-request-logs-freellmapi) Track FreeLLMAPI usage and request logs with built in analytics. Access aggregated metrics via authenticated REST endpoints for detailed insights. - Tags: how-to-guide - Published: 2026-06-24 ### [How to Configure Image Generation and Text-to-Speech Endpoints in FreeLLMAPI](/tashfeenahmed/freellmapi/configure-image-generation-tts-endpoints-freellmapi) Configure FreeLLMAPI for image generation and text-to-speech. Learn to set up provider rows and environment variables for OpenAI-compatible endpoints and automatic fallback. - Tags: how-to-guide - Published: 2026-06-24 ### [How to Use FreeLLMAPI with LangChain and LlamaIndex: Complete Integration Guide](/tashfeenahmed/freellmapi/use-freellmapi-with-langchain-llamaindex) Integrate FreeLLMAPI with LangChain and LlamaIndex seamlessly. This guide shows how to use the OpenAI-compatible API with simple configuration changes for self-hosted LLMs. - Tags: how-to-guide - Published: 2026-06-24 ### [How the Health Check Service Monitors Provider Keys in FreeLLMAPI](/tashfeenahmed/freellmapi/freellmapi-health-check-service-monitor-keys) Learn how FreeLLMAPI's health check service monitors provider keys, automatically disabling invalid ones and preserving those with transient network issues. - Tags: internals - Published: 2026-06-24 ### [LLM Providers Supported by FreeLLMAPI: Complete 2024 Integration Guide](/tashfeenahmed/freellmapi/supported-llm-providers-freellmapi) Discover which LLM providers FreeLLMAPI supports including Google Gemini Groq Mistral and more. Access 17+ LLM services via a single OpenAI compatible API. - Tags: getting-started - Published: 2026-06-24 ### [How Sticky Sessions Maintain Conversation Continuity in FreeLLMAPI](/tashfeenahmed/freellmapi/how-sticky-sessions-work-freellmapi) Learn how FreeLLMAPI uses sticky sessions and a unique session ID header to ensure seamless conversation continuity between stateless HTTP requests. - Tags: deep-dive - Published: 2026-06-24 ### [How AES-256-GCM Encryption Works for Stored API Keys in FreeLLMAPI](/tashfeenahmed/freellmapi/aes-256-gcm-encryption-api-keys-freellmapi) Learn how FreeLLMAPI secures API keys with AES-256-GCM encryption. Discover how it uses random IVs and authentication tags to protect your data. - Tags: deep-dive - Published: 2026-06-24 ### [How to Add a Custom OpenAI-Compatible Endpoint to FreeLLMAPI](/tashfeenahmed/freellmapi/add-custom-openai-compatible-endpoint-freellmapi) Learn to add a custom OpenAI-compatible endpoint to FreeLLMAPI. Register dynamic providers with a POST request to /keys/custom for seamless chat completion routing to your endpoint. - Tags: how-to-guide - Published: 2026-06-24 ### [Using Claude Code and Anthropic SDKs with FreeLLMAPI: A Complete Integration Guide](/tashfeenahmed/freellmapi/use-claude-code-anthropic-sdk-with-freellmapi) Integrate Claude Code and Anthropic SDKs with FreeLLMAPI effortlessly. This guide shows you how to leverage Claude models via OpenAI-compatible endpoints for seamless development. - Tags: getting-started - Published: 2026-06-24 ### [How FreeLLMAPI Handles Rate Limiting Across Different Providers](/tashfeenahmed/freellmapi/freellmapi-rate-limiting-across-providers) FreeLLMAPI manages rate limiting for various LLM providers using sliding-window counters and dynamic quota observation. Prevent quota exhaustion with escalating cooldowns. - Tags: deep-dive - Published: 2026-06-24 ### [How the FreeLLMAPI Fusion Panel Works: Multi-Model Synthesis Explained](/tashfeenahmed/freellmapi/how-does-the-freellmapi-fusion-panel-work) Discover how the FreeLLMAPI fusion panel achieves multi-model synthesis. Learn about parallel execution and output combination strategies for diverse LLM outputs. - Tags: deep-dive - Published: 2026-06-23 ### [How to Troubleshoot "All Models Exhausted" Errors in FreeLLMAPI](/tashfeenahmed/freellmapi/how-to-troubleshoot-all-models-exhausted-errors-in-freellmapi) Resolve 'All models exhausted' errors in FreeLLMAPI. Learn to fix rate limits, quota issues, and configuration problems for seamless model access. Get your FreeLLMAPI running smoothly! - Tags: how-to-guide - Published: 2026-06-23 ### [How FreeLLMAPI Health Checker Determines API Key Status](/tashfeenahmed/freellmapi/how-does-the-freellmapi-health-checker-determine-key-status) Discover how the FreeLLMAPI health checker validates API keys every 5 minutes using decryption and provider-specific methods, ensuring optimal performance and auto-disabling invalid keys. - Tags: how-to-guide - Published: 2026-06-23 ### [FreeLLMAPI Desktop App Features: Native Menu-Bar Client with Live Analytics](/tashfeenahmed/freellmapi/what-features-does-the-freellmapi-desktop-app-offer) Discover FreeLLMAPI desktop app features like its native menu-bar client, live analytics, and one-click dashboard access. Manage LLM APIs easily. - Tags: features - Published: 2026-06-23 ### [How to Add New LLM Providers to FreeLLMAPI: A Complete Implementation Guide](/tashfeenahmed/freellmapi/how-are-new-llm-providers-added-to-freellmapi) Learn how to add new LLM providers to FreeLLMAPI. Implement a class extending BaseProvider and register it to extend functionality. Get the complete implementation guide. - Tags: how-to-guide - Published: 2026-06-23 ### [What LLM Providers Are Supported by FreeLLMAPI? Complete 2025 Guide](/tashfeenahmed/freellmapi/what-llm-providers-are-supported-by-freellmapi) Access 17+ LLM providers like Gemini, Groq, and Mistral with FreeLLMAPI. Get free-tier access through a single OpenAI-compatible API. Learn more now. - Tags: getting-started - Published: 2026-06-23 ### [How Context Handoff Works in FreeLLMAPI: Preserving Conversation Continuity Across Model Switches](/tashfeenahmed/freellmapi/how-does-context-handoff-work-when-switching-models-in-freellmapi) Discover how FreeLLMAPI maintains conversation continuity with context handoff. Learn how synthesized system messages preserve session summaries across model switches without token overload. - Tags: deep-dive - Published: 2026-06-23 ### [How FreeLLMAPI Tracks RPM, RPD, TPM, and TPD for Rate Limiting](/tashfeenahmed/freellmapi/how-does-freellmapi-track-rpm-rpd-tpm-and-tpd-for-rate-limiting) Discover how FreeLLMAPI tracks RPM RPD TPM and TPD for effective rate limiting using SQLite persistence and in-memory sliding windows for low-latency lookups. - Tags: how-to-guide - Published: 2026-06-23 ### [What Routing Strategies Does FreeLLMAPI Support?](/tashfeenahmed/freellmapi/what-routing-strategies-does-freellmapi-support) Discover FreeLLMAPI routing strategies: priority, balanced, smartest, fastest, reliable, and custom. Optimize LLM requests by weight for reliability, speed, and intelligence. - Tags: how-to-guide - Published: 2026-06-23 ### [How FreeLLMAPI Implements API Key Encryption: AES-256-GCM Security Deep Dive](/tashfeenahmed/freellmapi/how-is-api-key-encryption-implemented-in-freellmapi) Learn how FreeLLMAPI secures provider API keys with AES-256-GCM encryption. Discover its robust key management and secure storage in SQLite, ensuring client data protection. - Tags: deep-dive - Published: 2026-06-23 ### [Environment Variables That Control FreeLLMAPI Behavior: Complete Configuration Guide](/tashfeenahmed/freellmapi/freellmapi-environment-variables-behavior-control) Discover the environment variables that control FreeLLMAPI behavior. Configure HTTP server, encryption, rate limiting, and more with this complete guide. - Tags: complete-configuration-guide - Published: 2026-06-22 ### [What Is the process-safety-net and How Does It Prevent Memory Leaks?](/tashfeenahmed/freellmapi/freellmapi-process-safety-net-memory-leaks) Discover how the process-safety-net global error handler stops memory leaks. Learn how it intercepts transient network errors to prevent process crashes and resource leaks in containers. - Tags: tutorial - Published: 2026-06-22 ### [How Fallback Chain Configuration Works in the FreeLLMAPI Dashboard](/tashfeenahmed/freellmapi/freellmapi-fallback-chain-configuration-dashboard) Learn how fallback chain configuration works in the FreeLLMAPI dashboard. Manage model order, penalties, and routing with our Express API and React interface. - Tags: how-to-guide - Published: 2026-06-22 ### [FreeLLMAPI Model Catalog Sync Mechanism: How It Fetches, Verifies, and Applies Updates](/tashfeenahmed/freellmapi/freellmapi-model-catalog-sync-mechanism-updates) Discover how FreeLLMAPI's model catalog sync mechanism fetches, verifies, and applies updates using cryptographically signed remote catalogs and atomic updates for reliable offline model management. - Tags: internals - Published: 2026-06-22 ### [How FreeLLMAPI Implements the Anthropic Messages API for Claude Clients](/tashfeenahmed/freellmapi/freellmapi-anthropic-messages-api-implementation) Learn how FreeLLMAPI implements the Anthropic Messages API for Claude clients. It handles authentication, validation, translation, and retries for seamless integration. - Tags: how-to-guide - Published: 2026-06-22 ### [How FreeLLMAPI Handles Context Handoff When Switching Models Mid-Conversation](/tashfeenahmed/freellmapi/freellmapi-context-handoff-model-switching) Learn how FreeLLMAPI seamlessly handles context handoff when switching models mid-conversation. Discover how recent history is transferred and summarized for uninterrupted AI chats. Explore FreeLLMAPI now. - Tags: internals - Published: 2026-06-22 ### [How Sticky Sessions Keep Conversations on the Same Model in FreeLLMAPI](/tashfeenahmed/freellmapi/freellmapi-sticky-sessions-feature-explained) Learn how FreeLLMAPI's sticky sessions ensure consistent AI conversations by binding them to the same model using a cache and deterministic session keys. Prevent mid-conversation model switching. - Tags: how-to-guide - Published: 2026-06-22 ### [How the Health Check Service Determines if a Provider Key is Healthy, Rate-Limited, or Invalid](/tashfeenahmed/freellmapi/freellmapi-health-check-service-provider-key-status) Learn how freellmapi's health check service validates provider keys. Discover status checks for healthy, rate-limited, and invalid keys by decrypting credentials and calling provider validateKey. - Tags: internals - Published: 2026-06-22 ### [FreeLLMAPI Provider Adapter Architecture: How to Add a New LLM Provider](/tashfeenahmed/freellmapi/freellmapi-provider-adapter-architecture-add-new) Learn the FreeLLMAPI provider adapter architecture. Easily integrate new LLM providers by extending the BaseProvider class and registering your instance. Simplify access to multiple LLM backends. - Tags: architecture - Published: 2026-06-22 ### [How the Automatic Fallback Mechanism Works in FreeLLMAPI for 429 and 5xx Errors](/tashfeenahmed/freellmapi/how-does-freellmapi-automatic-fallback-work) Discover how FreeLLMAPI automatically retries requests with fallback providers for 429 and 5xx errors, ensuring uninterrupted service by penalizing failed endpoints. - Tags: internals - Published: 2026-06-22