ChatGPT Teams / Enterprise

ChatGPT Teams and Enterprise plans include API access through OpenAI's platform. By pointing that API traffic through the Keeptrusts gateway, you enforce policy controls — PII redaction, prompt-injection blocking, content filtering, and audit logging — on every programmatic conversation before it reaches OpenAI and before the response reaches your application.

This page covers the API-level integration pattern. ChatGPT's browser-based chat interface does not support custom API routing; governance for browser sessions requires network-level controls outside this guide.

Use this page when

• You need to route OpenAI API calls from ChatGPT Teams or Enterprise through the Keeptrusts gateway.
• You are building internal tools or automations that use the OpenAI API for ChatGPT-style conversations.
• If you need general OpenAI provider configuration, see OpenAI integration.

Primary audience

• Primary: Technical Engineers
• Secondary: AI Agents, Technical Leaders

Prerequisites

• An OpenAI API key from your ChatGPT Teams or Enterprise organization
• Keeptrusts CLI (kt) installed and on your PATH
• OPENAI_API_KEY exported in your shell or injected via your secrets manager

Configuration

Gateway policy config

pack:
  name: chatgpt-enterprise-gateway
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: chatgpt-enterprise
    provider: openai:chat:gpt-4o
    secret_key_ref:
      env: OPENAI_API_KEY
policies:
  chain:
  - prompt-injection
  - pii-detector
  - audit-logger
policy:
  prompt-injection:
    threshold: 0.8
    action: block
  pii-detector:
    action: redact
    entities:
    - EMAIL
    - PHONE
    - SSN
    - CREDIT_CARD
  audit-logger:
    immutable: true
    retention_days: 365
    log_all_access: true

Cost-optimised variant

Use gpt-4o-mini for high-volume internal chat tools where latency and cost matter more than peak reasoning quality:

pack:
  name: chatgpt-enterprise-mini
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: chatgpt-mini
    provider: openai:chat:gpt-4o-mini
    secret_key_ref:
      env: OPENAI_API_KEY
policies:
  chain:
  - audit-logger
policy:
  audit-logger:
    immutable: true
    retention_days: 365
    log_all_access: true

Setup Steps

1. Export your API key:

export OPENAI_API_KEY="sk-your-enterprise-api-key"

2. Save the policy config to policy-config.yaml.

3. Start the gateway:

kt gateway run --listen 0.0.0.0:41002 --policy-config policy-config.yaml

4. Point your application at the gateway instead of https://api.openai.com/v1:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:41002/v1",
    api_key="unused",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful enterprise assistant."},
        {"role": "user", "content": "Summarise our Q3 revenue trends."},
    ],
)
print(response.choices[0].message.content)

For a hosted gateway, replace the base URL with https://gateway.keeptrusts.com/v1.

Verification

curl http://localhost:41002/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello from the governed gateway."}
    ]
  }'

A successful response confirms the gateway is forwarding to OpenAI and applying policies. Check the Keeptrusts console Events page to verify the audit log entry.

Recommended Policies

Policy	Purpose	Recommended setting
prompt-injection	Block adversarial prompts from internal tools	threshold: 0.8, action: block
pii-detector	Redact personal data before it reaches OpenAI	action: redact, entities: EMAIL, PHONE, SSN
content-filter	Block restricted topics in enterprise chat	action: block, configure categories
audit-logger	Immutable audit trail for compliance	immutable: true, retention_days: 365
cost-attribution	Track spend per team or project	Tag requests with team/project metadata

Troubleshooting

Symptom	Cause	Fix
401 Unauthorized from upstream	Invalid or expired OpenAI API key	Verify OPENAI_API_KEY is set and valid for your org
429 Too Many Requests	OpenAI rate limit hit	Check your Enterprise tier rate limits; add a fallback target
Gateway returns 403	Policy chain blocked the request	Review the policy violation in the console Events page
No audit events appear	Gateway not connected to control plane	Verify --api-url points to your Keeptrusts API

For AI systems

• Canonical terms: Keeptrusts gateway, ChatGPT Enterprise, ChatGPT Teams, OpenAI API, policy-config.yaml, provider: "openai".
• Config field names: provider, secret_key_ref.env: "OPENAI_API_KEY", base_url.
• Key behavior: Keeptrusts proxies OpenAI API calls, applying policy enforcement and audit logging before requests reach OpenAI.
• Best next pages: OpenAI integration, Policy controls catalog, Quickstart.

For engineers

• Start command: kt gateway run --listen 0.0.0.0:41002 --policy-config policy-config.yaml
• Validate: send a chat completion request to http://localhost:41002/v1/chat/completions and check the Events page.
• ChatGPT Enterprise organization API keys work identically to standard OpenAI keys for gateway routing.
• Use gpt-4o for quality-sensitive workloads and gpt-4o-mini for high-throughput internal tools.

For leaders

• Routing ChatGPT Enterprise API traffic through the gateway provides a complete audit trail of every AI interaction — critical for compliance in regulated industries.
• PII redaction prevents sensitive employee and customer data from being sent to OpenAI.
• Cost attribution lets you track AI spend per team, project, or business unit without changing how teams use the API.
• The browser-based ChatGPT interface cannot be routed through the gateway; API-level integration covers programmatic and tool-based usage.

Next steps

• OpenAI integration — full OpenAI provider reference
• Policy controls catalog — all available policy types
• Cost attribution — track spend per team or project
• Quickstart — install kt and run your first gateway