Provider OpenAI

OpenAI (GPT)

Use OpenAI's GPT and reasoning models to power your OpenClaw instances.

Overview

Detail	Value
Provider name in ClawFleet	openai
API key prefix	sk-*
Preset models	gpt-5.4, o3, gpt-5-mini
API docs	platform.openai.com/docs

Step 1: Get an API key

1. Go to platform.openai.com
2. Sign up or log in
3. Navigate to API keys (left sidebar, or Settings > API Keys)
4. Click Create new secret key
5. Give it a name and click Create
6. Copy the key — it starts with sk- and is only shown once

You'll need to add a payment method and purchase credits before making API calls.

Step 2: Add in Dashboard

1. Open the ClawFleet Dashboard (http://localhost:8080)
2. In the sidebar, click Assets > Model Config
3. Click + Add Model Config
4. Fill in the form:
   • Name: e.g. "GPT-5.4 Production"
   • Provider: select OpenAI
   • API Key: paste your sk-* key
   • Model: select gpt-5.4 (recommended), o3, or gpt-5-mini
5. Click Test — wait for "Validated" to appear
6. Click Configure to save

Step 3: Assign to an instance

1. Go to Fleet > Instances
2. Click Configure on the instance card
3. Select your OpenAI model config from the Model Config dropdown
4. Optionally select a channel config
5. Click Configure

Pricing notes

• OpenAI uses a prepaid credits model
• gpt-5.4 is the flagship model — best intelligence, 1M context window, $2.50/MTok input
• o3 is the strongest reasoning model — best for tasks requiring deep multi-step logic
• gpt-5-mini is fast and cost-effective — $0.25/MTok input, great for high-volume tasks
• Check openai.com/pricing for current rates

Troubleshooting

"Invalid API key (HTTP 401)"

• Verify you copied the full key including the sk- prefix
• Ensure the key hasn't been revoked in the OpenAI dashboard
• Check that you have credits on your account

"HTTP 429 — Rate limit exceeded"

• You've hit your rate limit — wait and retry, or upgrade your plan

Test passes but instance won't respond

• Ensure the instance is running (check the status on the instance card)
• Check instance logs via Desktop on the instance card