EmpirioLabs AI

Synap402 is an OpenAI-compatible inference API for open-weight models. Point any OpenAI SDK at it by changing the base URL and API key, pick a model, and existing code keeps working, including Cline, aider, opencode, Kilo Code, n8n, LangChain, Claude Code and Codex. The catalog lists 15 models, among them qwen3-coder-30b, gpt-oss-20b, Gemma 4 26B, Qwen3-VL 30B, Qwen3.5 122B, Muse Glimmer 30B and GLM-5.3, each with a published per-token price; gpt-oss-20b starts at $0.017 per million input tokens. Prompts are not used for training, data is not sold, and the prompt and completion text of API requests is not stored; only token counts, model and time are recorded for billing. Pay with prepaid credits that never expire (card from $10, TON or USDC from $1), an optional monthly plan, or per call in USDC over x402 with no account. An MCP server runs with npx synap-mcp. Free tier: 100,000 tokens a day on qwen3-coder-30b after Google sign-in, no card.

RankGPT is a Python toolkit designed to explore the use of generative Large Language Models (LLMs) like ChatGPT and GPT-4 for relevance ranking in Information Retrieval (IR). It introduces methods such as instructional permutation generation and a sliding window strategy to enable LLMs to effectively rerank documents. It supports various LLMs, including GPT-3.5, GPT-4, Claude, Cohere, and Llama2 via LiteLLM. RankGPT provides modules for retrieval, reranking, evaluation, and response analysis, facilitating end-to-end workflows. It includes a module for detailed analysis of input prompts and LLM responses, addressing reliability concerns with LLM APIs and non-deterministic behavior in Mixture-of-Experts (MoE) models. The toolkit supports various backends, including SGLang and TensorRT-LLM, and is compatible with a wide range of LLMs. RankGPT's Model Zoo includes models like LiT5 and MonoT5, hosted on Hugging Face.