one api for everything.

ai models, video rendering, email, search, project management. 250+ tools. call anything, compose everything.

terminal
$curl https://api.inference.sh/v1/run \
-H "Authorization: Bearer $KEY" \
-d '{"app":"flux-schnell","input":{"prompt":"a cat on mars"}}'
→ image generated in 3.2s
FLUXimage
Seedancevideo
Claudellm
Remotionrender
Gmailemail
Tavilysearch
Lineardev tools
Geminillm
Veovideo
SDXLimage
Slackcomms
Whisperaudio
Exasearch
Recraftimage
GitHubdev tools
Twittercomms
Notiondocs
GPTllm
FLUXimage
Seedancevideo
Claudellm
Remotionrender
Gmailemail
Tavilysearch
Lineardev tools
Geminillm
Veovideo
SDXLimage
Slackcomms
Whisperaudio
Exasearch
Recraftimage
GitHubdev tools
Twittercomms
Notiondocs
GPTllm
GPTllm
Notiondocs
Twittercomms
GitHubdev tools
Recraftimage
Exasearch
Whisperaudio
Slackcomms
SDXLimage
Veovideo
Geminillm
Lineardev tools
Tavilysearch
Gmailemail
Remotionrender
Claudellm
Seedancevideo
FLUXimage
GPTllm
Notiondocs
Twittercomms
GitHubdev tools
Recraftimage
Exasearch
Whisperaudio
Slackcomms
SDXLimage
Veovideo
Geminillm
Lineardev tools
Tavilysearch
Gmailemail
Remotionrender
Claudellm
Seedancevideo
FLUXimage
b
belt
the CLI for inference.sh. run tools, manage skills, connect MCP servers, all from your terminal.

why we built this

we've heard it all before

real quotes from developers hitting the same walls.

the moat

"The agent framework is not the moat. Prompt engineering is not the moat. The base LLM is not the moat. The specialized tools that encode domain knowledge—are the moat."

observability

"I spent 6 hours debugging a workflow that had zero error logs. When something breaks at 2 AM, I don't want to trace through 47 nodes. I want to see exactly what payload caused the issue."

durable execution

"I felt like a 'button person' in my IDE. The agent works in quanta—cut off by time every 2 minutes. Long tasks require pipeline thinking, not chat sessions."

real-time streaming

"Our multi-step agent produced great results but took 45+ seconds. Users thought it crashed. If they see the internal monologue, they wait. If they see a spinner, they leave."

pay-per-execution

"Spent 10 hours deploying agents on EC2... $13/mo per agent. Switched to serverless: 10 cents. Why is this so hard?"

decision context

"Systems record that a ticket was escalated, but not why it happened. Without that reasoning, agents treat every edge case as a brand new problem."

frequently asked questions

what is inference.sh?

inference.sh is a platform with 250+ tools, including AI models, dev tools, and integrations, callable through one API. it also includes a skill registry for AI agents, a production agent runtime, AI-native React components, and a team workspace.

how is inference.sh different from Replicate?

Replicate has AI models. inference.sh has AI models plus video rendering, email, search, project management, and MCP servers, all composable through one API. plus BYOK (bring your own keys) to route through Fal, Google, or your own GPUs.

do I need to build agents to use inference.sh?

no. call any tool with a single HTTP request. agents, skills, and teams are separate products on the same platform. use what you need.

what is BYOK?

bring your own keys. route model runs through Fal, Google, or your own GPUs. you're not locked in to any single provider.

ready to ship?

start with the hosted platform. deploy your own when you're ready.

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.