According to AlphaMoat, in the latest data month RunInfra (runinfra.ai) received 0 monthly visits — ranked #0 of 17,424 AI websites with traffic data, and #0 of 2,225 in General AI.
What is RunInfra
RunInfra is a hosted inference service for open-weight models, aimed at developers building agents. It exposes OpenAI- and Anthropic-compatible endpoints behind one API key, publishes per-model input, cached-input and output prices, and uses session-aware routing so repeat calls land on the replica already holding their context. The library lists models such as Nemotron 3.5 Lightning 30B, GLM 5.3 Flash and DeepSeek V4.1 Flash with measured cache hit rates and output speed.
- 01OpenAI- and Anthropic-compatible chat and messages APIs
- 02Session-aware routing that keeps repeat calls warm
- 03Cached input billed at the cached rate
- 04Published per-model input, cached input and output prices
- 05Coding plans for Claude Code, Codex and OpenCode
- 06Usage billed from one prepaid balance
Pay as you go runs on credit top-ups with a $5 minimum, billed per token from one balance. Coding plans start with Starter at $ 10 a month, Pro at $ 29 a month and Team at $ 99 a month, each resetting usage every 5 hours and every week. Enterprise is custom priced.
Popular in General AI
An all-in-one AI assistant for answering questions, writing, generating images, and coding.
+ Compare
A Google AI assistant combining writing, planning, and brainstorming.
+ Compare
An Anthropic AI assistant that analyzes files, code, and helps with writing.
+ Compare
An AI model developer focused on general intelligence foundation models and technology
+ Compare
An AI assistant that chats, generates images, writes code and connects to the web in real time
+ Compare
Data month: — · Visit figures are third-party traffic estimates aggregated monthly — best for scale and trends. Multiple domains of the same product are merged. See methodology.