Hostinger AI Router
Overview
| Property | Details |
|---|---|
| Description | Hostinger AI Router is a hosted, OpenAI-compatible gateway to OpenAI, Anthropic, Google, and other model families, billed in Hostinger credits. |
| Provider Route on LiteLLM | hostinger_router/ |
| Link to Provider Doc | Hostinger AI Router ↗ |
| Base URL | https://router.hostinger.com/v1 |
| Supported Operations | /chat/completions, /responses, /messages, /embeddings |
We support ALL Hostinger AI Router models, just set hostinger_router/ as a prefix when sending requests. The router's own model ids, such as claude-sonnet-5 or gpt-5.2, go after the prefix.
Available Models
| Model | Mode |
|---|---|
hostinger_router/claude-sonnet-5 | chat |
hostinger_router/gpt-5.2 | chat |
hostinger_router/text-embedding-3-small | embedding |
hostinger_router/text-embedding-3-large | embedding |
LiteLLM tracks spend for the models above, counting one Hostinger credit as $0.01. Any other model in the router's catalog also works with the hostinger_router/ prefix, but LiteLLM records its spend as $0 until a price is added, which you can set yourself through model_info on the proxy.
Every chat model works on /chat/completions, /responses, and /messages. When LiteLLM knows a model serves /v1/responses or /v1/messages on the router, such as gpt-5.2 on /responses or claude-sonnet-5 on /messages, it calls that route directly. For every other model, LiteLLM converts the call and sends it through the router's /v1/chat/completions.
Required Variables
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
Create an API key in the AI Router section of hPanel.
You can overwrite the base url with:
os.environ["HOSTINGER_ROUTER_API_BASE"] = "https://router.hostinger.com/v1"
Usage - LiteLLM Python SDK
Non-streaming
import os
from litellm import completion
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
response = completion(
model="hostinger_router/claude-sonnet-5",
messages=[{"content": "Hello, how are you?", "role": "user"}],
)
print(response)
Streaming
import os
from litellm import completion
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
response = completion(
model="hostinger_router/gpt-5.2",
messages=[{"content": "Hello, how are you?", "role": "user"}],
stream=True,
)
for chunk in response:
print(chunk)
Responses API
LiteLLM sends /responses calls for gpt-5.2 to the router's own /v1/responses endpoint, and converts calls for other models through /v1/chat/completions.
import os
import litellm
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
response = litellm.responses(
model="hostinger_router/gpt-5.2",
input="Name three primary colors",
)
print(response.output[0].content[0].text)
Anthropic Messages API
LiteLLM sends /messages calls for claude-sonnet-5 to the router's own /v1/messages endpoint, and converts calls for other models through /v1/chat/completions.
import asyncio
import os
import litellm
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
async def main():
response = await litellm.anthropic.messages.acreate(
model="hostinger_router/claude-sonnet-5",
messages=[{"role": "user", "content": "Name three primary colors"}],
max_tokens=200,
)
print(response["content"])
asyncio.run(main())
Embeddings
import os
import litellm
os.environ["HOSTINGER_ROUTER_API_KEY"] = "" # your Hostinger AI Router API key
response = litellm.embedding(
model="hostinger_router/text-embedding-3-small",
input=["hello from litellm"],
)
print(len(response.data[0]["embedding"]))
Usage - LiteLLM Proxy
Add the following to your LiteLLM Proxy configuration file:
model_list:
- model_name: hostinger-claude
litellm_params:
model: hostinger_router/claude-sonnet-5
api_key: os.environ/HOSTINGER_ROUTER_API_KEY
- model_name: hostinger-gpt
litellm_params:
model: hostinger_router/gpt-5.2
api_key: os.environ/HOSTINGER_ROUTER_API_KEY
- model_name: hostinger-embedding
litellm_params:
model: hostinger_router/text-embedding-3-small
api_key: os.environ/HOSTINGER_ROUTER_API_KEY
You can also add these models from the Admin UI. Open Models, click Add Model, pick Hostinger Router as the provider, and paste your API key.
Start your LiteLLM Proxy server:
export LITELLM_MASTER_KEY="sk-$(openssl rand -hex 32)"
printf 'Local proxy key: %s\n' "$LITELLM_MASTER_KEY"
litellm --config config.yaml
# RUNNING on http://0.0.0.0:4000
In another terminal, set LITELLM_API_KEY to the key printed above, then call the proxy:
- cURL
- OpenAI SDK
curl http://localhost:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "hostinger-claude",
"messages": [{"role": "user", "content": "hello from litellm"}]
}'
curl http://localhost:4000/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "hostinger-gpt",
"input": "hello from litellm"
}'
curl http://localhost:4000/v1/messages \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "hostinger-claude",
"max_tokens": 200,
"messages": [{"role": "user", "content": "hello from litellm"}]
}'
curl http://localhost:4000/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "hostinger-embedding",
"input": ["hello from litellm"]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:4000",
api_key=os.environ["LITELLM_API_KEY"],
)
response = client.chat.completions.create(
model="hostinger-claude",
messages=[{"role": "user", "content": "hello from litellm"}],
)
print(response.choices[0].message.content)
For more detailed information on using the LiteLLM Proxy, see the LiteLLM Proxy documentation.
