Codex

Codex talks to the OpenAI Responses API. ai& exposes an OpenAI-compatible /v1/responses endpoint, so any tool-calling model in our catalog can drive the agent loop.

Note

Codex 0.141+ speaks the Responses API only — the older chat-completions wire was removed — so wire_api = "responses" is required in the config below.

1. Install Codex

Prerequisite: Node.js 18 or newer.

macOS / Linux

npm install -g @openai/codex

Confirm the install — codex --version should print a version number:

codex --version

Windows (PowerShell)

npm install -g @openai/codex

Confirm the install — codex --version should print a version number:

codex --version

2. Set your API key

The config below reads your key from the AIAND_API_KEY environment variable, so Codex never stores it on disk.

macOS / Linux

export AIAND_API_KEY="sk-your-aiand-api-key"

Add that line to your ~/.zshrc or ~/.bashrc to persist it across terminals.

Windows (PowerShell)

$env:AIAND_API_KEY = "sk-your-aiand-api-key"

To persist it across sessions: setx AIAND_API_KEY "sk-your-aiand-api-key" (reopen the terminal afterward).

3. Add an ai& profile

Codex 0.141+ keeps each profile in its own file, ~/.codex/<name>.config.toml. Create ~/.codex/aiand.config.toml:

model = "zai-org/glm-5.2"
model_reasoning_effort = "high"
model_provider = "aiand"
web_search = "disabled"

[model_providers.aiand]
name = "ai&"
base_url = "https://api.aiand.com/v1"
env_key = "AIAND_API_KEY"
wire_api = "responses"

[tools]
view_image = false

[features]
unified_exec = false
apps = false
browser_use = false
browser_use_external = false
computer_use = false
image_generation = false
multi_agent = false
in_app_browser = false

The model_reasoning_effort line matters. Codex’s built-in default is medium, but supported reasoning levels vary by model: moonshotai/kimi-k3 accepts only high, low and max (anything else is rejected), and zai-org/glm-5.2 treats every value except high as its maximum — and most expensive — level. high is a safe, deliberate choice for every model recommended on this page.

The [features] block matters too. ai& serves standard function tools — which is all the coding agent loop needs — but not Codex’s hosted/built-in tools (web search, image generation, browser & computer control) or its grouped-tool wrapper. Left on, Codex can send tool types the API rejects (tool type … not supported), so the profile turns them off.

Save it in one step:

macOS / Linux

mkdir -p ~/.codex && cat > ~/.codex/aiand.config.toml <<'EOF'
model = "zai-org/glm-5.2"
model_reasoning_effort = "high"
model_provider = "aiand"
web_search = "disabled"

[model_providers.aiand]
name = "ai&"
base_url = "https://api.aiand.com/v1"
env_key = "AIAND_API_KEY"
wire_api = "responses"

[tools]
view_image = false

[features]
unified_exec = false
apps = false
browser_use = false
browser_use_external = false
computer_use = false
image_generation = false
multi_agent = false
in_app_browser = false
EOF

Windows (PowerShell)

New-Item -ItemType Directory -Force -Path $HOME\.codex | Out-Null
@'
model = "zai-org/glm-5.2"
model_reasoning_effort = "high"
model_provider = "aiand"
web_search = "disabled"

[model_providers.aiand]
name = "ai&"
base_url = "https://api.aiand.com/v1"
env_key = "AIAND_API_KEY"
wire_api = "responses"

[tools]
view_image = false

[features]
unified_exec = false
apps = false
browser_use = false
browser_use_external = false
computer_use = false
image_generation = false
multi_agent = false
in_app_browser = false
'@ | Set-Content -Encoding utf8 $HOME\.codex\aiand.config.toml

Tip

zai-org/glm-5.2, moonshotai/kimi-k3 and deepseek-ai/deepseek-v4-pro are strong tool-callers and a good default for the agent loop. Any model with the tool_calling capability in the catalog works — swap the model line to switch, and keep model_reasoning_effort = "high", which all three support.

4. Run Codex

codex --profile aiand

Or non-interactively — --full-auto lets the agent edit files in the workspace:

codex exec --profile aiand --full-auto "Fix the failing test in src/math.js"

Verify

Probe the wire-level path from the shell — a match means the key authenticates and the model is on your org:

macOS / Linux

curl -sS https://api.aiand.com/v1/models \
  -H "Authorization: Bearer $AIAND_API_KEY" \
  | grep -o 'zai-org/glm-5.2'

Windows (PowerShell)

(Invoke-RestMethod https://api.aiand.com/v1/models `
  -Headers @{ Authorization = "Bearer $env:AIAND_API_KEY" }).data.id `
  | Select-String "zai-org/glm-5.2"

Caution

A few things to expect:

• ERROR: Reconnecting… five times, then We're currently experiencing high demand — usually not load. This is how Codex surfaces a model rejecting the request, most often a model_reasoning_effort the model doesn’t support (Codex defaults to medium when the line is missing). Set it to a level the model supports — high works for every model recommended here.
• tool type … not supported — a built-in tool is still enabled. Make sure the [features] block and web_search = "disabled" are present in your profile.
• warning: Model metadata for '…' not found — harmless. Codex ships metadata only for OpenAI’s own models and falls back to safe defaults for ai& models.
• unsupported call: apply_patch in the logs — harmless. Codex falls back to shell commands to edit files when the host doesn’t expose its patch tool.