1curl -fsSL https://cli.inference.sh | sh

1infsh login

1mkdir my-app && cd my-app2infsh init

1my-app/2├── inf.yml           # Configuration3├── inference.py      # Your code4├── requirements.txt  # Dependencies5└── ...

1from inferencesh import BaseApp, BaseAppInput, BaseAppOutput, File2from pydantic import Field3from typing import Optional4 5class AppInput(BaseAppInput):6    prompt: str = Field(description="What to generate")7    style: str = Field(default="default", description="Output style")8 9class AppOutput(BaseAppOutput):10    result: str = Field(description="Generated text")11    image: Optional[File] = Field(default=None, description="Generated image")12 13class App(BaseApp):14    async def setup(self, metadata):15        """Called once when the worker starts.16        Load models, initialize resources here."""17        pass18    19    async def run(self, input_data: AppInput, metadata) -> AppOutput:20        """Called for each request.21        Process input and return output."""22        23        # Access inputs24        prompt = input_data.prompt25        style = input_data.style26        27        # Log progress (visible in real-time)28        metadata.log("Processing...")29        30        # Do your work31        result = f"Generated: {prompt} in {style} style"32        33        # Return output34        return AppOutput(result=result)35    36    async def unload(self):37        """Called on shutdown. Cleanup resources."""38        pass

1async def run(self, input_data: AppInput, metadata) -> AppOutput:2    # File is ready to use3    image_path = input_data.image.path4    5    with open(image_path, "rb") as f:6        data = f.read()

1async def run(self, input_data: AppInput, metadata) -> AppOutput:2    # Write to a file3    output_path = "/tmp/result.png"4    save_image(output_path)5    6    # Return it7    return AppOutput(image=File(path=output_path))

1name: my-app2description: What my app does3category: image4 5resources:6  gpu:7    count: 18    vram: 8000       # MB9    type: nvidia10  ram: 16000         # MB11 12python: "3.11"

1torch>=2.0.02transformers>=4.30.03pillow>=9.0.0

1ffmpeg2libgl1-mesa-glx

1# inf.yml2requirements:3  # Environment secrets (user provides their own keys)4  secrets:5    - key: OPENAI_API_KEY6      description: For GPT-4 API calls7    8    - key: REPLICATE_API_TOKEN9      description: For model inference10      optional: true11 12  # Integrations (managed OAuth connections)13  integrations:14    - key: google.sheets15      description: Read/write spreadsheets16    17    - key: x.tweet.write18      description: Post tweets19      optional: true

1infsh deploy

1┌──────────────────────────────────────┐2│         deployment summary           │3├──────────────────────────────────────┤4│                                      │5│ final status: success                │6│ duration: 45s                        │7│ user: yourname                       │8│ app: my-app                          │9│ link: https://app.inference.sh/...   │10│                                      │11└──────────────────────────────────────┘

1infsh run --save-example2# Creates input.json

1infsh run --input-file input.json

1# Skip validation for faster deploys2infsh deploy --skip-checks

1❌ Don't: One app that does everything2✓ Do: Single-purpose apps that compose well

1async def setup(self, metadata):2    # Good: Download on first run, cached afterward3    from huggingface_hub import hf_hub_download4    self.model_path = hf_hub_download("model-name", "model.bin")

1async def run(self, input_data: AppInput, metadata) -> AppOutput:2    metadata.log("Step 1: Loading image...")3    # ...4    metadata.log("Step 2: Processing...")5    # ...6    metadata.log("Step 3: Saving result...")

1async def run(self, input_data: AppInput, metadata) -> AppOutput:2    if not input_data.image.exists():3        raise ValueError("Image file not found")4    5    try:6        result = process(input_data)7    except ProcessingError as e:8        metadata.log(f"Error: {e}")9        raise RuntimeError(f"Processing failed: {e}")