### Start Codex project

Source: https://modelflare.dev/docs/codex

Commands to initialize a project directory and start the Codex CLI.

```powershell
Set-Location $HOME
New-Item -ItemType Directory -Force "my-codex-project" | Out-Null
Set-Location "my-codex-project"
codex --model gpt-5.6-sol
```

```bash
cd ~
mkdir -p my-codex-project
cd my-codex-project
codex --model gpt-5.6-sol
```

--------------------------------

### Install Gemini CLI

Source: https://modelflare.dev/docs/gemini-cli

Install the latest version of the Gemini CLI globally via npm and verify the installation.

```bash
npm install -g @google/gemini-cli@latest
gemini --version
```

--------------------------------

### Start OpenCode

Source: https://modelflare.dev/docs/opencode

Initializes the OpenCode interface within the project directory.

```bash
opencode
```

--------------------------------

### Start and Test Connection

Source: https://modelflare.dev/docs/grok-build

Verify the configuration by running a test prompt through the Grok CLI.

```powershell
Set-Location $HOME
grok -p "Reply only: Modelflare connected" -m modelflare-grok
grok

```

```bash
cd ~
grok -p "Reply only: Modelflare connected" -m modelflare-grok
grok

```

--------------------------------

### Install OpenCode CLI

Source: https://modelflare.dev/docs/opencode

Commands to install the OpenCode CLI on different operating systems.

```powershell
choco install opencode
opencode --version
```

```bash
curl -fsSL https://opencode.ai/install | bash
opencode --version
```

--------------------------------

### Install Grok Build CLI

Source: https://modelflare.dev/docs/grok-build

Commands to download and install the Grok CLI on different operating systems.

```powershell
irm https://x.ai/cli/install.ps1 | iex
grok version

```

```bash
curl -fsSL https://x.ai/cli/install.sh | bash
grok version

```

--------------------------------

### Start and Test Gemini CLI

Source: https://modelflare.dev/docs/gemini-cli

Initialize the CLI with a specific model ID and send a test message to verify connectivity.

```bash
gemini --model YOUR_MODEL_ID
```

```text
Reply with one sentence confirming the connection is working.
```

--------------------------------

### Install Codex CLI manually

Source: https://modelflare.dev/docs/codex

Commands to download and verify the Codex CLI installation.

```powershell
irm https://chatgpt.com/codex/install.ps1 | iex
codex --version
```

```bash
curl -fsSL https://chatgpt.com/codex/install.sh | sh
codex --version
```

--------------------------------

### Start and test Claude Code

Source: https://modelflare.dev/docs/claude-code

Commands to launch the CLI and verify the connection.

```bash
claude
```

```text
Reply with one sentence confirming the active model.
```

--------------------------------

### Install Claude Code CLI

Source: https://modelflare.dev/docs/claude-code

Commands to install the Claude Code CLI tool on different operating systems.

```powershell
irm https://claude.ai/install.ps1 | iex
claude --version
```

```bash
curl -fsSL https://claude.ai/install.sh | bash
claude --version
```

--------------------------------

### Install Codex via automated script

Source: https://modelflare.dev/docs/codex

Use these commands to automatically install or update Codex on your system.

```bash
curl -fsSL https://modelflare.dev/install/codex.sh | sh
```

```bash
curl -fsSL https://modelflare.dev/install/codex.sh | MODELFLARE_ALLOW_ROOT=1 sh
```

```powershell
irm https://modelflare.dev/install/codex.ps1 | iex
```

--------------------------------

### Verify Codex CLI connection

Source: https://modelflare.dev/docs/codex

Run this command in a new terminal session to verify the installation and active model.

```bash
codex --model gpt-5.6-sol
```

--------------------------------

### Create config.toml

Source: https://modelflare.dev/docs/codex

Commands to generate the configuration file with provider settings.

```powershell
$config = @'
model_provider = "modelflare"
model = "gpt-5.6-sol"
model_reasoning_effort = "xhigh"
disable_response_storage = true
model_supports_reasoning_summaries = true

[model_providers.modelflare]
name = "Modelflare"
base_url = "https://modelflare.dev/v1"
wire_api = "responses"

[model_providers.modelflare.auth]
command = "powershell.exe"
args = ["-NoProfile", "-NonInteractive", "-Command", "Get-Content -LiteralPath (Join-Path (Join-Path $HOME '.codex') 'modelflare_api_key') -Raw"]
'@
$utf8NoBom = New-Object System.Text.UTF8Encoding -ArgumentList $false
[System.IO.File]::WriteAllText(
  (Join-Path (Get-Location) "config.toml"),
  $config,
  $utf8NoBom
)
```

```bash
cat > config.toml << 'EOF'
model_provider = "modelflare"
model = "gpt-5.6-sol"
model_reasoning_effort = "xhigh"
disable_response_storage = true
model_supports_reasoning_summaries = true

[model_providers.modelflare]
name = "Modelflare"
base_url = "https://modelflare.dev/v1"
wire_api = "responses"

[model_providers.modelflare.auth]
command = "sh"
args = ["-lc", "cat ~/.codex/modelflare_api_key"]
EOF
chmod 600 config.toml
```

--------------------------------

### Create config.toml

Source: https://modelflare.dev/docs/grok-build

Create the configuration file required to define the Modelflare model backend.

```powershell
New-Item -ItemType Directory -Force "$HOME\.grok" | Out-Null
Set-Location "$HOME\.grok"
$config = @'
[models]
default = "modelflare-grok"

[model.modelflare-grok]
model = "grok-4.5"
base_url = "https://modelflare.dev/v1"
name = "Modelflare Grok 4.5"
env_key = "MODELFLARE_API_KEY"
api_backend = "responses"
'@
$utf8NoBom = New-Object System.Text.UTF8Encoding -ArgumentList $false
[System.IO.File]::WriteAllText(
  (Join-Path (Get-Location) "config.toml"),
  $config,
  $utf8NoBom
)

```

```bash
mkdir -p ~/.grok
cd ~/.grok
cat > config.toml << 'EOF'
[models]
default = "modelflare-grok"

[model.modelflare-grok]
model = "grok-4.5"
base_url = "https://modelflare.dev/v1"
name = "Modelflare Grok 4.5"
env_key = "MODELFLARE_API_KEY"
api_backend = "responses"
EOF
chmod 600 config.toml

```

--------------------------------

### Create modelflare_api_key file

Source: https://modelflare.dev/docs/codex

Commands to save your API key securely in the configuration directory.

```powershell
$apiKey = @'
YOUR_MODELFLARE_API_KEY
'@
$apiKey = $apiKey.Trim()
$utf8NoBom = New-Object System.Text.UTF8Encoding -ArgumentList $false
[System.IO.File]::WriteAllText(
  (Join-Path (Get-Location) "modelflare_api_key"),
  $apiKey,
  $utf8NoBom
)
$apiKey = $null
```

```bash
cat > modelflare_api_key << 'EOF'
YOUR_MODELFLARE_API_KEY
EOF
chmod 600 modelflare_api_key
```

--------------------------------

### Create .codex directory

Source: https://modelflare.dev/docs/codex

Commands to initialize the required configuration directory.

```powershell
New-Item -ItemType Directory -Force "$HOME\.codex" | Out-Null
Set-Location "$HOME\.codex"
```

```bash
mkdir -p ~/.codex
cd ~/.codex
```

--------------------------------

### Test Model Connection

Source: https://modelflare.dev/docs/opencode

A sample prompt to verify that the model is correctly configured and responding.

```text
Reply with one short greeting.
```

--------------------------------

### Create Claude Code settings file

Source: https://modelflare.dev/docs/claude-code

Commands to create the configuration file with Modelflare API credentials and model aliases.

```powershell
New-Item -ItemType Directory -Force "$HOME\.claude" | Out-Null
Set-Location "$HOME\.claude"
$settings = @'
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://modelflare.dev",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_MODELFLARE_API_KEY",
    "ANTHROPIC_MODEL": "claude-opus-4-8",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-opus-4-8",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-5",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-sonnet-5"
  }
}
'@
$utf8NoBom = New-Object System.Text.UTF8Encoding -ArgumentList $false
[System.IO.File]::WriteAllText(
  (Join-Path (Get-Location) "settings.json"),
  $settings,
  $utf8NoBom
)
```

```bash
mkdir -p ~/.claude
cd ~/.claude
cat > settings.json << 'EOF'
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://modelflare.dev",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_MODELFLARE_API_KEY",
    "ANTHROPIC_MODEL": "claude-opus-4-8",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-opus-4-8",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-5",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-sonnet-5"
  }
}
EOF
chmod 600 settings.json
```

--------------------------------

### Create opencode.json Configuration

Source: https://modelflare.dev/docs/opencode

Generates the required configuration file for Modelflare integration in the project directory.

```powershell
$config = @'
{
  "$schema": "https://opencode.ai/config.json",
  "model": "modelflare/deepseek-v4-pro",
  "provider": {
    "modelflare": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Modelflare",
      "options": { "baseURL": "https://modelflare.dev/v1" },
      "models": {
        "deepseek-v4-pro": { "name": "DeepSeek V4 Pro" }
      }
    }
  }
}
'@
$utf8NoBom = New-Object System.Text.UTF8Encoding -ArgumentList $false
[System.IO.File]::WriteAllText(
  (Join-Path (Get-Location) "opencode.json"),
  $config,
  $utf8NoBom
)
```

```bash
cat > opencode.json << 'EOF'
{
  "$schema": "https://opencode.ai/config.json",
  "model": "modelflare/deepseek-v4-pro",
  "provider": {
    "modelflare": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Modelflare",
      "options": { "baseURL": "https://modelflare.dev/v1" },
      "models": {
        "deepseek-v4-pro": { "name": "DeepSeek V4 Pro" }
      }
    }
  }
}
EOF
```

--------------------------------

### Test Codex model response

Source: https://modelflare.dev/docs/codex

Use this prompt to confirm that the model and provider are correctly configured.

```text
Reply with one sentence confirming the active model and provider.
```

--------------------------------

### Configure Modelflare Environment Variables

Source: https://modelflare.dev/docs/gemini-cli

Set the required environment variables to point the Gemini CLI to the Modelflare API endpoint.

```powershell
$env:GEMINI_API_KEY="YOUR_MODELFLARE_API_KEY"
$env:GOOGLE_GEMINI_BASE_URL="https://modelflare.dev"
```

```bash
export GEMINI_API_KEY="YOUR_MODELFLARE_API_KEY"
export GOOGLE_GEMINI_BASE_URL="https://modelflare.dev"
```

--------------------------------

### Troubleshooting CLI commands

Source: https://modelflare.dev/docs/codex

Commands used to resolve common errors or environment issues.

```bash
codex.cmd
```

--------------------------------

### Save API Key

Source: https://modelflare.dev/docs/grok-build

Set the Modelflare API key as an environment variable for the current session and future terminal instances.

```powershell
[Environment]::SetEnvironmentVariable(
  "MODELFLARE_API_KEY",
  "YOUR_MODELFLARE_API_KEY",
  "User"
)
$env:MODELFLARE_API_KEY = "YOUR_MODELFLARE_API_KEY"

```

```bash
echo 'export MODELFLARE_API_KEY="YOUR_MODELFLARE_API_KEY"' >> ~/.bashrc
source ~/.bashrc

```

```bash
echo 'export MODELFLARE_API_KEY="YOUR_MODELFLARE_API_KEY"' >> ~/.zshrc
source ~/.zshrc

```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.