Commands
Global Options
These options apply to all commands:
| Flag | Description | Default |
|---|---|---|
--format <type> | Output format: table, json, yaml | table |
--api-url <url> | API base URL | https://api.openmodels.run |
--api-key <key> | API authentication key | — |
--no-color | Disable colored output | false |
--verbose | Show detailed error information | false |
-v, --version | Show CLI version | — |
-h, --help | Show help | — |
models list
List models with optional filters and sorting.
openmodels models list [options]Options:
| Flag | Description |
|---|---|
--capability <type> | Filter by capability (e.g. chat, completion, embedding) |
--modality <type> | Filter by modality (e.g. text, image, audio) |
--sort <field> | Sort by field (e.g. context_window, name, created_at) |
--limit <n> | Maximum number of results |
Examples:
# List all models
openmodels models list
# Filter by capability, sort by context window
openmodels models list --capability chat --sort context_window
# Get top 10 models as JSON
openmodels models list --limit 10 --format jsonmodels info
Show detailed information about a specific model.
openmodels models info <model-id>Examples:
openmodels models info claude-opus-4-6
openmodels models info gpt-4o --format yamlproviders list
List inference providers.
openmodels providers list [options]Options:
| Flag | Description |
|---|---|
--search <query> | Filter providers by name |
Examples:
# List all providers
openmodels providers list
# Search for a specific provider
openmodels providers list --search anthropiccompare
Compare providers for a given model side-by-side.
openmodels compare <model-id> [options]Options:
| Flag | Description |
|---|---|
--sort <field> | Sort by: price, latency, uptime |
Examples:
# Compare all providers for GPT-4o
openmodels compare gpt-4o
# Sort by price
openmodels compare gpt-4o --sort price
# Output as JSON for further processing
openmodels compare claude-opus-4-6 --format jsonsearch
Full-text search across models.
openmodels search <query> [options]Options:
| Flag | Description |
|---|---|
--limit <n> | Maximum number of results |
Examples:
openmodels search "code generation" --limit 10
openmodels search "vision" --format jsontelemetry
View provider health status and latency metrics.
openmodels telemetry <provider-id> [options]Options:
| Flag | Description |
|---|---|
--period <duration> | Time period (e.g. 24h, 7d, 30d) |
Examples:
# Check Anthropic telemetry
openmodels telemetry anthropic
# Last 7 days
openmodels telemetry openai --period 7d
# Machine-readable output
openmodels telemetry together-ai --format jsoncompletions
Generate shell completion scripts.
openmodels completions <shell>Supported shells: bash, zsh, fish.
Setup:
# Bash
openmodels completions bash >> ~/.bashrc
# Zsh
openmodels completions zsh > ~/.zfunc/_openmodels
# Fish
openmodels completions fish > ~/.config/fish/completions/openmodels.fishAfter adding completions, restart your shell or source the config file.
Last updated on