Results for “llm-api”

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Batch-process pending LLM Gateway account-contribution requests through the admin API: preflight, validate, issue, patch, and refresh usage with deterministic proxy assignment.

Guides building LLM applications on the Dify platform, covering visual workflows, knowledge bases, agents, and API deployment.

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `llm-router`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Deploy and serve LLMs in production with vLLM, Ollama, TGI, and llama.cpp, including quantization and GPU optimization.

China LLM Gateway - Unified interface for Chinese LLMs including Qwen, DeepSeek, GLM, Baichuan. OpenAI compatible, one API Key for all models. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Configure tools and SDKs to route LLM requests through a single API key with native-compatible endpoints for Claude, GPT, and Gemini, including setup, base URLs, and code examples.

Access 100+ LLMs including Claude, Gemini, Kimi, and GLM via the inference.sh CLI with automatic fallback and cost optimization.

Portkey AI gateway — unified LLM API, load balancing, fallbacks, caching, guardrails, observability

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.

Imports local Kiro CLI accounts into StaticFlow/llm-access by reading SQLite auth files and calling the local admin API, with proxy assignment and validation.

交互式 API key 配置引导 — 检测当前 .env 状态，逐步引导配置 Semantic Scholar、DeepXiv 和 Review LLM

Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.

Guides users through configuring a LaRuche node by reading its live API state and providing click paths for settings, including LLM providers, messaging channels, secrets vault, MCP server, and memory.

Debug LLM applications using the Phoenix CLI: fetch traces, analyze errors, structure trace review with open and axial coding, inspect datasets, review experiments, and query the GraphQL API.

Builds RAG and agent applications with LlamaIndex, covering installation, LlamaParse, and LlamaAgents.

Provides a persistent memory CLI for LLM agents, installed via npx.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.

Train, fine-tune, and deploy LLMs using LitGPT's clean implementations of 20+ architectures like Llama, Gemma, and Phi.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.

Enforces production-grade Python and AI engineering standards for FastAPI, LangChain/LangGraph, RAG pipelines, and LLM integrations, covering type safety, error handling, testing, and security.

Build automated evaluation pipelines for Python LLM applications using real LLM calls and structured test datasets.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.