built-in
hundreds of apps
image generation, video, audio, chat, search, and more. run any model with a single API call. pay per run, no subscriptions.
tools
any ai model. one api call.
image, video, audio, text, search, 3D. one key, pay per run, zero vendor lock-in.
app store
allimagevideoaudio3d
flux-dev
pruna
tts
elevenlabs
veo-3
google
seedance
bytedance
gpt-image-2
openai
wan-2.7
alibaba
pruna/flux-dev7.9scompleted
three sources of tools
built-in. connected. composed.
every tool funnels into the same interface. where it comes from doesn't matter. same shape, same API.
connected
MCP connectors
browse and add connectors. linear, notion, slack, github. your agent gets access to thousands of tools through the open standard.
composed
flows become tools
chain any tools into a flow. the result is callable like any other tool. AI models, non-AI tools, connectors, other flows. all composable.
categories
250+ tools across every category.
image
FLUX Dev
Seedream
Recraft
GPT Image
video
Seedance 2
Veo 3
Remotion
Wan 2.7
chat
Claude Opus
Gemini 3
GPT-4o
Grok
audio
ElevenLabs TTS
Kokoro
Dia TTS
social
X / Twitter
Slack
Gmail
dev tools
Linear
GitHub
Notion
search
Tavily
Tavily Extract
utilities
Shell
Browser
Image Resize
also available as an MCP server
use from claude code, cursor, or any MCP client
add one line to your MCP config. every tool on inference shell becomes available to your agent.
mcp config
{
"mcpServers": {
"inference": {
"url": "https://api.inference.sh/mcp"
}
}
}one api call
run any tool in three lines.
terminal
import Inference from '@inference/sdk'
const client = new Inference()
const result = await client.run('pruna/flux-dev', {
prompt: 'a marble workbench with glowing tools'
})
console.log(result.image)
// → https://cloud.inference.sh/...
output
pruna/flux-dev · 7.9s · $0.005
sdks: javascript · python · go · cli
built to stay useful
one api. your keys. durable execution.
one api
same interface for every tool. built-in or connected, same shape: input in, output out. no per-provider SDKs.
byok
bring your own keys. route model runs through fal, google, or your own GPUs. you're not locked in.
durable
every tool call retries on failure, persists state, and tracks execution. built in, not bolted on.
an ai runtime where everything compounds. run any model, compose agents, stack knowledge. also includes a skill registry, connectors, and a team workspace.
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.