Skip to content
InferenceHub

Quickstart

Three steps from zero to a live response. No credit card — every new account starts with $1 in free credit.
1

Create an account and API key

Sign up at the portal and create a key. It looks like sk-prov-live-… and is shown once — copy it now. You can revoke it and create a new one at any time.

2

Make your first request

The gateway speaks both major wire formats — use whichever your code already uses. OpenAI format (base URL ends in /v1):

curl https://app.inferencehub.tech/v1/chat/completions \
-H "Authorization: Bearer sk-prov-live-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.2",
"messages": [{"role": "user", "content": "Say hello in five words."}]
}'

Anthropic format (base URL is the bare origin — the client appends /v1/messages):

curl https://app.inferencehub.tech/v1/messages \
-H "x-api-key: sk-prov-live-YOUR_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "sonnet",
"max_tokens": 256,
"messages": [{"role": "user", "content": "Say hello in five words."}]
}'
3

Or drop it into an SDK

The official SDKs work unchanged — set the base URL and your key, keep everything else:

from openai import OpenAI
client = OpenAI(
base_url="https://app.inferencehub.tech/v1",
api_key="sk-prov-live-YOUR_KEY",
)
response = client.chat.completions.create(
model="glm-5.2",
messages=[{"role": "user", "content": "Say hello in five words."}],
)
print(response.choices[0].message.content)
import anthropic
client = anthropic.Anthropic(
base_url="https://app.inferencehub.tech",
api_key="sk-prov-live-YOUR_KEY",
)
message = client.messages.create(
model="sonnet",
max_tokens=256,
messages=[{"role": "user", "content": "Say hello in five words."}],
)
print(message.content[0].text)

The JavaScript/TypeScript SDKs take the same two parameters (baseURL, apiKey).

See which models your key reaches

One key reaches every enabled model — switch by changing the model field, never the key. List the live ids (the .data[].id shape works for any client):

curl -s https://app.inferencehub.tech/v1/models \
-H "Authorization: Bearer sk-prov-live-YOUR_KEY" | jq -r '.data[].id'

Model ids, short aliases, and naming rules are on the Models page.

Next steps