curl -fsSL https://cli.inference.sh | sh

infsh update   # Update CLI
infsh login    # Authenticate
infsh me       # Check current user

infsh app init my-app              # Create app (interactive)
infsh app init my-app --lang node  # Create Node.js app

infsh app init my-app

cd my-app                          # ALWAYS cd into app dir first
infsh app test --save-example      # Generate sample input from schema
infsh app test                     # Run with input.json
infsh app test --input '{"prompt": "hello"}'  # Or inline JSON

cd my-app                          # cd again — cwd doesn't persist
infsh app deploy --dry-run         # Validate first
infsh app deploy                   # Deploy for real

infsh app run user/app --json --input '{"prompt": "hello"}'

# Other useful commands
infsh app run user/app --input input.json
infsh app sample user/app
infsh app sample user/app --save input.json

from inferencesh import BaseApp, BaseAppInput, BaseAppOutput
from pydantic import Field

class AppSetup(BaseAppInput):
    """Setup parameters — triggers re-init when changed"""
    model_id: str = Field(default="gpt2", description="Model to load")

class AppInput(BaseAppInput):
    prompt: str = Field(description="Input prompt")

class AppOutput(BaseAppOutput):
    result: str = Field(description="Output result")

class App(BaseApp):
    async def setup(self, config: AppSetup):
        """Runs once when worker starts or config changes"""
        self.model = load_model(config.model_id)

    async def run(self, input_data: AppInput) -> AppOutput:
        """Default function — runs for each request"""
        self.logger.info(f"Processing prompt: {input_data.prompt[:50]}")
        result = self.model.generate(input_data.prompt)
        self.logger.info("Generation complete")
        return AppOutput(result=result)

    async def unload(self):
        """Cleanup on shutdown"""
        pass

    async def on_cancel(self):
        """Called when user cancels — for long-running tasks"""
        return True

import { z } from "zod";

export const AppSetup = z.object({
  modelId: z.string().default("gpt2").describe("Model to load"),
});

export const RunInput = z.object({
  prompt: z.string().describe("Input prompt"),
});

export const RunOutput = z.object({
  result: z.string().describe("Output result"),
});

export class App {
  async setup(config) {
    /** Runs once when worker starts or config changes */
    this.model = loadModel(config.modelId);
  }

  async run(inputData) {
    /** Default function — runs for each request */
    return { result: "done" };
  }

  async unload() {
    /** Cleanup on shutdown */
  }

  async onCancel() {
    /** Called when user cancels — for long-running tasks */
    return true;
  }
}

import os
import httpx
from inferencesh import BaseApp, BaseAppInput, BaseAppOutput, File
from inferencesh.models.usage import OutputMeta, ImageMeta  # or TextMeta, AudioMeta, etc.
from pydantic import Field

class AppInput(BaseAppInput):
    prompt: str = Field(description="Input prompt")

class AppOutput(BaseAppOutput):  # NOT BaseModel — output_meta requires this
    image: File = Field(description="Generated image")

class App(BaseApp):
    async def setup(self, config):
        self.api_key = os.environ["API_KEY"]
        self.client = httpx.AsyncClient(timeout=120)

    async def run(self, input_data: AppInput) -> AppOutput:
        self.logger.info(f"Calling API with prompt: {input_data.prompt[:80]}")

        response = await self.client.post(
            "https://api.example.com/generate",
            headers={"Authorization": f"Bearer {self.api_key}"},
            json={"prompt": input_data.prompt},
        )
        response.raise_for_status()

        # Write output file
        output_path = "/tmp/output.png"
        with open(output_path, "wb") as f:
            f.write(response.content)

        # Read actual dimensions (don't hardcode!)
        from PIL import Image
        with Image.open(output_path) as img:
            width, height = img.size

        self.logger.info(f"Generated {width}x{height} image")

        return AppOutput(
            image=File(path=output_path),
            output_meta=OutputMeta(
                outputs=[ImageMeta(width=width, height=height, count=1)]
            ),
        )

    async def unload(self):
        await self.client.aclose()

my-app/
├── inf.yml           # Configuration
├── inference.py      # App logic
├── requirements.txt  # Python packages (pip)
└── packages.txt      # System packages (apt) — optional

my-app/
├── inf.yml           # Configuration
├── src/
│   └── inference.js  # App logic
├── package.json      # Node.js packages (npm/pnpm)
└── packages.txt      # System packages (apt) — optional

name: my-app
description: What my app does
category: image
kernel: python-3.11     # or node-22

# For multi-function apps (default: run)
# default_function: generate

resources:
  gpu:
    count: 1
    vram: 24    # 24GB (auto-converted)
    type: any
  ram: 32       # 32GB

env:
  MODEL_NAME: gpt-4

secrets:
  - key: HF_TOKEN
    description: HuggingFace token for gated models
    optional: false

integrations:
  - key: google.sheets
    description: Access to Google Sheets
    optional: true

resources:
  gpu:
    count: 0
    type: none
  ram: 4

torch>=2.0
transformers
accelerate

{
  "type": "module",
  "dependencies": {
    "zod": "^3.23.0",
    "sharp": "^0.33.0"
  }
}

ffmpeg
libgl1-mesa-glx