Get Started with FriendliAI

Create a FriendliAI API key, send your first request, and learn to control a model’s capabilities. Once you complete these steps, you’re ready to choose a popular model and use your favorite agent or SDK with FriendliAI. With Friendli Model APIs, you get access to a curated set of popular, open-weight models that are ready for you today. If you want to run any model — including your own — on dedicated GPUs, try Friendli Dedicated Endpoints. To get started, complete the following steps.

Create an API Key

Create a Friendli Suite Account

If you haven’t already, sign up for an account.

Then, sign in. Friendli Suite opens your dashboard.

Create a FriendliAI API Key

In the left sidebar, click Settings. Then, click API Keys.
In the upper-right corner, click Create API Key.
(Optional) Name your API key and set an expiration date.
Click Create Key.
Click Copy.

Send a Request

Set Up Your API Key

In your terminal, run the following command:

export FRIENDLIAI_API_KEY="<FRIENDLIAI_API_KEY>"

Replace <FRIENDLIAI_API_KEY> with your API key.

Install the OpenAI SDK

In your terminal, run the following command:

pip install openai

npm install openai

Send Your Request to FriendliAI

Run the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.2",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.2",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.2",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ]
}'

FriendliAI returns a response, similar to the following:

{
  "id": "chatcmpl-04eb40ba7fc14cf8a51b7869d9cfa76f",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "FriendliAI is a generative AI infrastructure company that provides optimized solutions to help businesses deploy large language models faster, more efficiently, and at a lower cost.",
        "reasoning": "...",
        "reasoning_content": "..."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "created": 1781892285,
  "usage": {
    "completion_tokens": 412,
    "prompt_tokens": 27,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 439
  },
  "model": "zai-org/GLM-5.2"
}

Control a Capability

You can control most capabilities — such as streaming or reasoning — with parameters, which you pass as either request body parameters or chat template keyword arguments. How you pass each depends on the parameter:

Turn Streaming On

Some request body parameters are processed by the Friendli Engine and natively by an SDK.For example, to turn streaming on, run the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

stream = client.chat.completions.create(
  model="zai-org/GLM-5.2",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  stream=True,
)

for chunk in stream:
  print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const stream = await client.chat.completions.create({
  model: "zai-org/GLM-5.2",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "stream": true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0].delta?.content || "")
}

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.2",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "stream": true
}'

Set the Reasoning Budget

Other request body parameters are processed exclusively by the Friendli Engine and are used to further shape the response.For example, to set the reasoning budget to 10,000 tokens, run the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.2",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "reasoning_budget": 10000,
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.2",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "reasoning_budget": 10000,
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.2",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "reasoning_budget": 10000
}'

Preserve Reasoning

Chat template keyword arguments are always forwarded to the model’s chat template and used to construct the prompt to the model’s specifications.For example, to preserve reasoning, run the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.2",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "chat_template_kwargs": {
      "clear_thinking": False,
    },
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.2",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "chat_template_kwargs": {
    "clear_thinking": false,
  },
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.2",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "chat_template_kwargs": {
      "clear_thinking": false
    }
}'

Congratulations. You learned to control a model’s capabilities and are ready to build your next project.

Use Popular Models and Your Favorite Agent or SDK

You’re ready to start building with your favorite coding agent or SDK to connect to fast, cost-efficient, and reliable open-weight models.

Models

Use popular FriendliAI models.

Agents

Use your favorite agent with FriendliAI.

SDKs

Use your favorite SDK with FriendliAI.

Introduction

Capabilities

Friendli Model APIs

Friendli Dedicated Endpoints

Friendli Container

Friendli Suite Guide

Get Started with FriendliAI

Create an API Key

Send a Request

Control a Capability

Use Popular Models and Your Favorite Agent or SDK

Models

Agents

SDKs

​Create an API Key

​Send a Request

​Control a Capability

​Use Popular Models and Your Favorite Agent or SDK

Models

Agents

SDKs

Create an API Key

Send a Request

Control a Capability

Use Popular Models and Your Favorite Agent or SDK