InferAll
One API key for 120+ AI models across OpenAI, Anthropic Claude, Google Gemini, NVIDIA NIM, Replicate, and Runway. 25+ free open-source models, published per-tok
Quick answer
What is InferAll?
At a glance
- Category
- Hosting & Devtools
- Pricing
- Open Source
- Starting price
- Not disclosed
- Free tier
- No
- Platforms
- Not disclosed
- Launched
- Not disclosed
- Company
- Not disclosed
About InferAll
One API key for 120+ AI models across OpenAI, Anthropic Claude, Google Gemini, NVIDIA NIM, Replicate, and Runway. 25+ free open-source models, published per-token pricing on premium providers. InferAll is an Anthropic-compatible gateway with $0 input/output on 25+ NVIDIA-hosted open-source models. The published wizard is several releases behind and has a number of known problems, including a doctor command that can call a committed .env safe, and an init that may leave your key written but not gitignored.
From the community
User reviews
No user reviews yet. Be the first to share your experience with InferAll.
Alternatives
Similar to InferAll
Getsocialclaw
The SocialClaw social media CLI posts and schedules to X, LinkedIn, Instagram, TikTok, YouTube, and more from your terminal. JSON output, schedule files in git, validation...
Scalix World
Scalix World is the AI-native neocloud: database, AI inference, functions, containers, and storage on one platform, operable by humans and AI agents.
HeimWall
Signal, not surveillance. See how your engineers use Cursor, Claude Code, and Copilot: catch leaked secrets, PII, and confidential data, without blocking them or reading...
docs.dev
Point your coding agent at your repo and your docs; it opens a docs branch, your team reviews on the rendered page, publishing is a commit. Runs on your Cloudflare, no...
Kalytera
Works with LangChain, CrewAI, AutoGen, or any custom framework.
Forth MCP
Works with Claude, ChatGPT, and any MCP client Give any AI client access to.
Techavy is reader supported. When you buy through links on our site we may earn an affiliate commission. This never changes our ratings or what we recommend. See our methodology.