Skip to main content

CLI Commands

Complete reference for all PolarGrid CLI commands.

Authentication

Login

Opens browser for OAuth authentication:
For CI/CD, use environment variable instead:

Whoami

Shows your current authentication context:
Output:

Organizations

List Organizations

Shows all organizations you’re a member of, with your role in each.

Switch Organization

API Keys

Create Key

Options:
  • -p, --permissions <level>: read-only, read-write, or admin (default: read-write)
  • --project <id>: Scope key to a specific project
Copy your API key immediately — you won’t be able to see it again!

Revoke Key

Inference

Chat

Interactive streaming chat with edge models:
Options:
  • -r, --region <region>: Edge region
  • -m, --model <model>: Model (default: qwen-3.5-27b)
  • -s, --system <prompt>: System prompt
  • -t, --temperature <n>: Temperature 0.0-2.0 (default: 0.7)
  • --no-interactive: Single-shot mode, no follow-up
In interactive mode, type /exit or /quit to end the conversation.

Completions

Generate text completions:
Options:
  • -r, --region <region>: Edge region
  • -m, --model <model>: Model (default: qwen-3.5-27b)
  • --max-tokens <n>: Maximum tokens (default: 200)
  • -t, --temperature <n>: Temperature 0.0-2.0 (default: 0.7)

Text-to-Speech

Convert text to audio:
Options:
  • -r, --region <region>: Edge region
  • -m, --model <model>: TTS model (default: kokoro-82m)
  • -v, --voice <voice>: Voice (default: af_bella)
  • -f, --format <format>: mp3, wav, opus, flac (default: mp3)
  • -o, --output <file>: Output file (default: output.<format>, e.g., output.mp3)
  • --speed <n>: Speed 0.25-4.0 (default: 1.0)
Available voices: alloy, echo, fable, onyx, nova, shimmer, af_bella, af_sarah, am_adam, am_michael, bf_emma, bf_isabella, bm_george, bm_lewis

Transcribe

Transcribe audio to text:
Options:
  • -r, --region <region>: Edge region
  • -m, --model <model>: STT model (default: whisper-large-v3-turbo)
  • -l, --language <lang>: Language code (e.g., en, fr, es)
  • -f, --format <format>: text, json, srt, vtt, verbose_json (default: text)
  • -o, --output <file>: Output file (default: stdout)

Translate

Translate audio to English:
Options:
  • -r, --region <region>: Edge region
  • -m, --model <model>: STT model (default: whisper-large-v3-turbo)
  • -f, --format <format>: text, json (default: text)
  • -o, --output <file>: Output file (default: stdout)

Models

Manage models on edge servers. Requires POLARGRID_API_KEY.

List Models

Model Status

Shows which models are loaded, loading, or failed with colored status indicators.

GPU

Monitor and manage GPU resources. Requires POLARGRID_API_KEY.

GPU Status

Shows GPU name, utilization %, memory usage, temperature, and running processes.

GPU Memory

Visual bar chart of memory usage per GPU.

Regions

List Regions

Shows all regions with current latency from your location.

Ping Regions

Shows min/avg/max latency to each region.

Testing

Health Check

Inference Test

Options:
  • -r, --region <region>: Target region (required unless default set)
  • -m, --model <model>: Model to use (default: qwen-3.5-27b)
  • -p, --prompt <prompt>: Prompt to send (default: “Hello, how are you?”)

Shell Completions

This is polargrid completion (singular) — not to be confused with polargrid completions (text inference).
Install completions for your shell:

Configuration

Available Config Options

Examples

Configuration Files

The CLI stores configuration in ~/.polargrid/: Set POLARGRID_DISABLE_KEYCHAIN=1 to force the encrypted-file backend. An existing plaintext credentials.json from an older CLI is migrated into the encrypted store on first use and then deleted.

CI/CD Example