Provider: FriendliAI
Call FriendliAI models through Respan Gateway with unified logs, cost, and latency.
Use Respan Gateway to call FriendliAI Serverless Endpoints (GLM 5.3, DeepSeek, and other models) while keeping unified observability (logs, cost, latency, reliability) in Respan.
Quick setup
Get a Respan API key
Sign up and create a key on the API keys page .
Add credits (recommended)
Top up credits to pay through Respan. No Friendli key required, Respan handles provider auth and billing.
Prefer to route through your own Friendli account? See Use your own FriendliAI key.
Send your first request
Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.
FriendliAI is OpenAI-compatible. Point the OpenAI SDK at the Respan gateway and call any Friendli model.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_RESPAN_API_KEY",
base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
model="friendliai/zai-org/GLM-5.3",
messages=[{"role": "user", "content": "Hello, Friendli!"}],
)
print(response.choices[0].message.content)More integrations
FriendliAI models work with every Respan gateway integration:
Switch models
Change the model parameter to call any supported model through the same client. Use the friendliai/ prefix to disambiguate when routing across providers. Browse the full list on the Models page .
client.chat.completions.create(model="friendliai/zai-org/GLM-5.3", messages=messages)
client.chat.completions.create(model="friendliai/zai-org/GLM-5.3-Flash", messages=messages)
client.chat.completions.create(model="friendliai/zai-org/GLM-5.2", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)Use your own FriendliAI key (BYOK)
Credits are the default path. If you’d rather bill Friendli directly, attach your own provider key.
Open Providers
Go to the Providers page .
Add FriendliAI
Select FriendliAI and paste your friendli.api_key (Friendli Suite Personal API key).
Load balancing (Optional)
Add multiple credential sets and use Load balancing weight to distribute traffic across them.
Override credentials per model (Optional)
Use credential_override when one model on a request should use a different Friendli key than the default.
{
"customer_credentials": {
"friendli": { "api_key": "YOUR_FRIENDLI_API_KEY" }
},
"credential_override": {
"friendliai/zai-org/GLM-5.3": { "api_key": "ANOTHER_FRIENDLI_API_KEY" }
}
}Log without proxying (Optional)
Already calling Friendli directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.
import requests
requests.post(
"https://api.respan.ai/api/request-logs/create/",
headers={
"Authorization": "Bearer YOUR_RESPAN_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "friendliai/zai-org/GLM-5.3",
"prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
"completion_message": {"role": "assistant", "content": "Hello from FriendliAI through Respan."},
"cost": 0.001,
"generation_time": 1.2,
"customer_params": {"customer_identifier": "user_123"},
},
)See the logging guide for the full setup.