API keys

API keys authenticate your applications against aixplain. One key lets you run and create agents, models, and tools through the SDK, the REST API, or the OpenAI-compatible API.

Manage keys at app.aixplain.com/team/settings?tab=api-keys (Team settings → API keys). Each workspace can hold up to 10 keys.

warning

Keys are workspace-specific and cannot be moved between workspaces. To use a key elsewhere, create a new one in that workspace.

---

Create a key

1. Go to Team settings → API keys and click Create API key.
2. Give it a descriptive name, for example Production web app.
3. Optionally set an expiration date; leave it blank for a key that never expires.
4. Click Create, then copy the key immediately — the full secret is shown only once.

If you lose a key, delete it and create a new one; the secret cannot be retrieved again. Each key row shows its name, creator, created and expiration dates, status, and the last few characters for identification.

---

Use a key

aixplain SDK (Python)

from aixplain import Aixplain

aix = Aixplain(api_key="YOUR_API_KEY")

# Run an agent
agent = aix.Agent.get("agent-id")
print(agent.run(query="What is the weather today?").data.output)

# Run a model
model = aix.Model.get("model-id")
print(model.run(text="Translate to French: Hello").data)

# Create and save a new agent
new_agent = aix.Agent(
    name="Support agent",
    description="Answers customer questions",
    instructions="Be concise and helpful.",
).save()
print(new_agent.id)

REST API

Pass the key in the x-api-key header (see Integration):

curl -X POST "https://platform-api.aixplain.com/v2/agents/AGENT_ID/run" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "What is the weather today?"}'

OpenAI-compatible API

For models that support the OpenAI format:

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.aixplain.com/v1")

response = client.chat.completions.create(
    model="model-id",
    messages=[{"role": "user", "content": "Hello!"}],
)

---

Rate limits

Standard keys run inference. Admin keys (Owners and Admins only) do not run inference — they set per-model rate and usage limits on LLMs, whether a model is called directly or used inside an agent. Creating, updating, monitoring, and enforcing those limits is covered in Rate limiting.

---

Security

• Never commit a key to version control — use environment variables or a secrets manager (AWS Secrets Manager, Azure Key Vault, HashiCorp Vault, CI/CD secrets).
• Use a separate key per application, so you can revoke one without affecting the others.
• Rotate keys periodically and delete keys for retired applications.
• Never put a key in client-side code (for example, browser JavaScript).

Deleting a key revokes it immediately and cannot be undone — any application still using it will get authentication errors. In a personal workspace only you can delete a key; in a team workspace, Admins and Owners can.

---

Troubleshooting

Error	Likely cause	Fix
Invalid API key	Key deleted, expired, mistyped, or from another workspace	Confirm the key is active in the correct workspace and copied in full
Rate limit exceeded	Admin-key limits, or too many concurrent requests	Check the key's limits; add exponential backoff; reduce request frequency
Insufficient credits	Workspace is out of credits	Add credits (see Credits and billing) and set a low-credit alert