A developer built a Go CLI that benchmarks LLMs via OpenRouter's API, testing accuracy, instruction following, tool calling, and JSON compliance. In a comparison of free-tier models, the smaller Ling …
A developer reports that the AI harness Pi from pi.dev ignored MCP server instructions and deviated from project skills during a Clojure-to-Common-Lisp port, while the Goose harness from Goose-docs.ai…
A developer open-sourced Pawmc, a self-hosted LLM assistant that runs on Cloudflare Workers and Durable Objects, with user-steered compounding of context across sessions. The project costs $0 on Cloud…
Cline CLI, the open-source AI coding agent used by 160,000 developers in VS Code, is now available for CI pipelines like GitHub Actions and GitLab CI with version 3.0.45, which reduced the npm install…
9Router has released 9router-Python, a Python SDK and CLI for its AI gateway that routes requests to 35 models across providers including Gemini, NVIDIA, OpenRouter, Groq, Ollama, Tavily, and Exa. The…
On July 30, OpenAI cut the input price of GPT-5.6 Luna by 80% from $1.00 to $0.20 per million tokens and output from $6.00 to $1.20, while Terra dropped 20% and Sol gained a Fast mode at double the pr…
OpenRouter launched Ori Eval, a tool that lets developers evaluate and compare AI models on their own prompts, data, and harness to identify the best model for their specific application. The tool sca…
FLock has added DeepSeek V4 Flash to its OpenAI-compatible API Platform, offering developers access to a 284-billion-parameter mixture-of-experts model with a 1-million-token context window at discoun…
A potential US ban on Chinese open-weight AI models could cost American businesses up to US$12 billion per year, according to Daniel Yue, an assistant professor at the Georgia Institute of Technology'…
Chinese API resellers are selling Claude and Codex tokens at up to 90% discounts, or 10% of official prices, according to a Show HN post on 2 August by xiaoxumz11 and a May ChinaTalk analysis by Zilan…
Vercel AI Gateway charges zero markup on provider list prices, while OpenRouter adds a 5.5% fee on credit purchases, but OpenRouter offers broader model coverage and more provider redundancy, accordin…
Z.ai's GLM-5.2 scored 62.1 on SWE-bench Pro, beating GPT-5.5's 58.6, while costing $1.40 per million input tokens and $4.40 per million output tokens, making it 3.6x cheaper on input and 5.7x cheaper …
A developer building RAG and agent features in Python found that token cost control became a third of the work, and discovered that a thin router in front of an app can provide one API key across Open…
Rails Agent, a new fullstack framework for building autonomous AI agents natively in Ruby on Rails, was announced on Hacker News. The framework allows developers to build, test, deploy, and monitor ag…
Microsoft's VS Code 1.131, released on July 29, introduces subagent visibility in the Agents window, built-in offline dictation powered by Microsoft's Nemotron model, and Bring Your Own Key (BYOK) sup…
MarketDaily, a daily financial email digest serving 21 subscribers, uses a 9-model LLM council with a judge and a 31-check deterministic audit gate to generate personalized reports, but has experience…
60 Minute Creator, a new AI video generation platform, lets users connect their own API keys from Fal AI, Kie AI, and OpenRouter instead of buying platform credits, enabling direct billing and access …
LangGraph, a framework by LangChain, is the focus of a new enterprise guide detailing production-ready AI agent middleware patterns, including human-in-the-loop interrupts, LLM gateways, security midd…
Anthropic's Claude Code terminal coding agent can be configured to route through OpenRouter's API, which exposes an Anthropic-compatible endpoint, allowing users to use a single OpenRouter API key and…
DeepSeek released DeepSeek-V4-Flash-0731 on July 31st, an MIT-licensed model with API prices of $0.14 per million cache-miss input tokens and $0.28 per million output tokens, aiming to lower cost barr…