10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 1205 ms

1. 1awesome-free-llm-apisdemo or tutorialno passport yet

   skillreason-machines/trending-skillsrecord

   • awesome-free-llm-apis

     Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns.

2. 2free-llm-api-hubfound in code, not yet checkedno passport yet

   MCP serverpacocartones/free-llm-api-hub

   • search_providers

     Search the free-llm-api-hub dataset of free-tier and trial-credit LLM API providers.

   • openai_client_config

     For a provider listed in the published openai-clients.json (verified, OpenAI-compatible, with a base URL):

3. 3ia-qa mcp llm and RAG testing - Dev/QA toolboxverified and signedpassport

   MCP serverrecord

   • llm_generate

     Generate text using open-source LLM models hosted on Groq (ultra-fast) or HuggingFace Inference (serverless). No API key required — the server provides its own keys. Supported models: Qwen3 32B, Gemma 4 27B, Gemma 3 27B, Llama 3.3 70B, Llama 4 Scout, DeepSeek R1, Mistral Small 24B, and more. Use lis

4. 4llm-modelsverified and signedpassport

   skillinference-sh/skillsrecord

   • llm-models

     Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generati

5. 5NeuroDynamic Audio and LLM APIsfound in code, not yet checkedno passport yet
   • catalogue

     Read free services, voices, schema or cloning requirements. No wallet or payment needed.

   • quote

     Get a free verified USDC/Base quote: narration, transcription, abliterated or abliterated-large. No input uploaded or funds spent.

6. 6OAuth Multi-LLM Orchestratorverified and signedpassport

   agentrecord

   • Self-test (free verification)

     FREE — no payment, no API key, no signup. Runs this agent's REAL capability on fixed canned input and returns the genuine result, an honest assertion grade (`asserted_correct` = a property of the output was checked; `ran_without_error` = it ran but nothing was asserted, which is NOT a pass), a trust

7. 7llm_api_searchfound in code, not yet checkedno passport yet

   MCP serverendaoshea/llm_api_search

   • llm_list_providers

     List all supported LLM API providers (e.g. anthropic, google, openai, inception, deepseek, zai, minimax).

8. 8free-apis-collectionfound in code, not yet checkedno passport yet

   MCP servergaupoit/free-apis-collection

   • call_api

     Call a free API endpoint and return the response.