RunInfra
Updated
About RunInfra
RunInfra is an API service that runs open-source language models with caching and fast responses.
Developers and teams building AI agents use RunInfra to access open models cheaply and quickly. The service works well for projects where agents send similar context repeatedly, since cached requests cost much less than fresh ones.
- Access to open models like DeepSeek, GLM, and Qwen
- Prompt caching that reduces input token costs
- Compatible with OpenAI and Anthropic SDKs
- Session-aware routing keeps repeat calls on the same server
Good to know: Starter plan is $10 per month with usage included. Works with OpenAI and Anthropic client libraries.
Key features
- Prompt caching: Reused context costs as little as $0.01 per million tokens, with cache hit rates up to 99%.
- Session routing: Automatically keeps related API calls on the same server to maximize cache hits without extra setup.
- One API key: Single authentication works with both OpenAI and Anthropic SDKs without code changes.
At a glance
- Category: AI Coding
- Type: AI model & API platform
- Jobs: Build Sites & Apps
- Evidence: New launch on Product Hunt (a few reviews)
- AIME Score: 54 of 100
- Launched: Oct 20, 2026 on Product Hunt · 100+ upvotes
- Website: runinfra.ai
Alternatives to RunInfra
- Azure OpenAI Service (AIME Score 65)
- Llama (AIME Score 64)
- AWS Bedrock (AIME Score 64)
- Wiro (AIME Score 63)
- Apiframe (AIME Score 63)
- Mistral AI (AIME Score 61)
More AI model & API platform tools
Sources: Found on Product Hunt (launched Oct 2026) · Details checked on the tool’s own website · Researched by AI Made Easy
This is a tool profile with the essentials. Spotlights, our in-depth reviews with screenshots and video, are added every day, Proven tools first. How we pick Spotlights
Is this your tool? Claim, update or remove this listing, or get a badge