> ## Documentation Index
> Fetch the complete documentation index at: https://runinfra.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# What is RunInfra?
> RunInfra turns plain English into production AI inference endpoints. Describe your use case and the AI agent builds, optimizes, and deploys it for you.
RunInfra is an AI-powered platform that lets you describe the endpoint you need in plain English and handles everything else: model selection, GPU benchmarking, optimization, deployment, and scaling. Whether you're building a low-latency chatbot, a batch summarization API, or a multi-model reasoning pipeline, you go from idea to live endpoint without writing infrastructure code.
**No YAML. No DevOps. No GPU configuration. Just chat.**
## What you can build
RunInfra can build large language model, speech-to-text, text-to-speech, embedding, vision-language, and image-generation pipelines when the selected model and runtime support the route. Six pre-built use cases ship as starting points you can fork in chat.
Streaming STT, LLM, and TTS fused on one GPU at sub-600ms turn-taking.
Llama, Hermes, Qwen with tool use, streaming, and structured output.
BGE encoders + cross-encoder reranker fused on one GPU in one round-trip.
Hybrid retrieval, grounded generation, citation spans you can audit.
Qwen2.5-VL and Llama 3.2 Vision parsing PDFs and forms to JSON.
Open Whisper with diarization and PII redaction.
### Example prompts
Copy any of these into the [dashboard](https://runinfra.ai/~) chat to see how it works.
```text Chatbot theme={"dark"}
Deploy Llama 3.1 8B as a low-latency customer support chatbot.
Optimize for latency, keep P99 under 200ms.
```
```text Routing theme={"dark"}
Build a multi-model pipeline: Phi-3 Mini for simple queries,
Llama 70B for complex reasoning. Budget is $300/month.
```
```text Summarizer theme={"dark"}
Optimize Qwen 2.5 14B for throughput and deploy as a batch
summarization API. Max $0.003 per request.
```
```text Code theme={"dark"}
I need a code generation endpoint using DeepSeek V3.
Keep cost under $0.005 per request.
```
The agent handles model selection, GPU benchmarking, optimized variant search, kernel optimization, deployment, and autoscaling.
## How it works
A four-stage workflow from description to live endpoint.
```mermaid theme={"dark"}
flowchart LR
User[You]
Agent[RunInfra agent]
Optimizer[Optimizer]
Cloud[RunInfra Cloud]
Endpoint[OpenAI-compatible endpoint]
App[Your app]
User -- plain English --> Agent
Agent -- builds pipeline --> Optimizer
Optimizer -- GPU profiling + variant search + Forge kernels --> Cloud
Cloud -- deploy --> Endpoint
App -- OpenAI SDK --> Endpoint
```
Tell RunInfra what you need in plain English. The agent asks clarifying questions when needed, then builds your pipeline automatically.
Real GPU profiling across L4 to B200, Hugging Face variant search (AWQ, GPTQ, FP8), and Forge kernel tuning. Results stream in real time.
One click ships an OpenAI-compatible endpoint. Flex (scale-to-zero) or Active (always-on). Cold starts under 2 seconds.
OpenAI Python and JavaScript SDKs, curl, and documented framework integrations use your RunInfra base URL and deployed model ID.
## Why RunInfra
Closed-source APIs charge per token with no control over latency, throughput, or cost. With RunInfra you own the model and the infrastructure. RunInfra optimizes GPU kernels so your open-source models run as fast as, or faster than, proprietary APIs at a fraction of the cost.
## Get started
Your first pipeline in 5 minutes.
Pre-built workflows you can fork in chat.
Decision table by use case and priority.
Flex vs Active, deployment targets, scaling.