Skip to main content
API7.ai Logo

OpenAI

Connect AISIX AI Gateway to OpenAI so applications can call GPT models through the gateway's OpenAI-compatible API. AISIX keeps the OpenAI credential on the gateway side. It authorizes model access with caller API keys and allowlists, and applies the same rate-limit and usage-accounting controls as other model aliases.

OpenAI is the gateway's native OpenAI-compatible upstream. It uses the openai adapter and is the only provider where api_base is optional.

Prerequisites​

The following examples use a self-hosted AISIX gateway. Before configuring the upstream, prepare the following:

Configure the OpenAI Upstream​

Create a provider key, model alias, and caller API key for the OpenAI-backed route.

Create a Provider Key​

Create the provider key that stores the OpenAI credential:

# Replace with your values
export AISIX_ADMIN_KEY="YOUR_ADMIN_KEY"
export OPENAI_API_KEY="YOUR_PROVIDER_API_KEY"

curl -sS -X POST "http://127.0.0.1:3001/admin/v1/provider_keys" \
  -H "Authorization: Bearer ${AISIX_ADMIN_KEY}" \
  -H "Content-Type: application/json" \
  --data-binary @- <<EOF
  {
    "display_name": "openai-prod",
    "provider": "openai",
    "adapter": "openai",
    "secret": "${OPENAI_API_KEY}"
  }
EOF

❶ provider is openai. This is the only provider value that lets AISIX fall back to the default base URL https://api.openai.com/v1.

❷ adapter selects the OpenAI wire format.

❸ secret stores the OpenAI API key. It follows the credential-handling behavior in Provider Credentials.

You can omit api_base for OpenAI. To target a compatible OpenAI endpoint such as an Azure-fronted proxy or a regional gateway, set api_base explicitly. Copy the returned provider key ID.

Create a Model​

Create the model alias callers will send in requests:

# Replace with your values
export PROVIDER_KEY_ID="YOUR_PROVIDER_KEY_ID"

curl -sS -X POST "http://127.0.0.1:3001/admin/v1/models" \
  -H "Authorization: Bearer ${AISIX_ADMIN_KEY}" \
  -H "Content-Type: application/json" \
  --data-binary @- <<EOF
  {
    "display_name": "gpt-4o-prod",
    "provider": "openai",
    "model_name": "gpt-4o",
    "provider_key_id": "${PROVIDER_KEY_ID}"
  }
EOF

❶ display_name is the alias callers send in model.

❷ model_name is the OpenAI model ID, for example gpt-4o or gpt-4o-mini.

❸ provider_key_id attaches the alias to the OpenAI provider key.

Create a Caller API Key​

Choose the caller API key value that the application will send to AISIX, then hash it for the admin resource:

# Replace with your values
export AISIX_API_KEY="YOUR_CALLER_API_KEY"

CALLER_KEY_HASH=$(printf '%s' "${AISIX_API_KEY}" | shasum -a 256 | awk '{print $1}')

Create the caller API key resource that can access the model alias:

curl -sS -X POST "http://127.0.0.1:3001/admin/v1/apikeys" \
  -H "Authorization: Bearer ${AISIX_ADMIN_KEY}" \
  -H "Content-Type: application/json" \
  --data-binary @- <<EOF
  {
    "key_hash": "${CALLER_KEY_HASH}",
    "allowed_models": ["gpt-4o-prod"]
  }
EOF

The allowed_models value must match the model alias you created.

The gateway hashes and stores caller keys as key_hash; the raw key is never stored. Provider key secrets are returned as *** in Admin API list views.

Verify the Provider Connection​

Send a chat-completions request through the AISIX proxy:

curl -sS -X POST "http://127.0.0.1:3000/v1/chat/completions" \
  -H "Authorization: Bearer ${AISIX_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-prod",
    "messages": [
      {
        "role": "user",
        "content": "Say hello from OpenAI."
      }
    ]
  }'

The gateway returns an OpenAI-compatible response that echoes the caller-facing alias gpt-4o-prod. Confirm the request on the OpenAI usage dashboard. If the request fails with an upstream authentication error, check the provider key secret.

Use an OpenAI SDK​

Point OpenAI SDK clients at the gateway by setting the base URL to http://127.0.0.1:3000/v1 and the API key to the caller key. See the OpenAI SDK Quickstart.

Next Steps​

You have now connected AISIX to OpenAI and verified the model alias. Continue with these guides: