Friendli AI

Verified 💳 Trial Credits

FriendliAI serverless Model APIs: an OpenAI-compatible endpoint optimized for latency and throughput. New accounts get trial credits at onboarding (the amount is not published). Current lineup includes GLM-5.3, GLM-5.3 Flash, GLM-5.2, GLM-5.1, Gemma 4 31B and DeepSeek V3.2.

$10 Credits Low Latency Enterprise OpenAI Compatible
Get API Key Suggest Edit
1

Overview

Provider Type

Trial Credits

API Endpoint

https://inference.friendli.ai/v1

Free Tier Highlights

60 RPM

Why Choose Friendli AI?

FriendliAI's serverless Model APIs focus on low latency and high throughput. The lineup is strong for coding: GLM-5.3, GLM-5.3 Flash, GLM-5.2 and GLM-5.1, plus Gemma 4 31B.

Best for: benchmarking the GLM-5 family on a fast, production-oriented service.

Watch out: free use is a one-time trial credit given at onboarding (amount not published), not a recurring free tier.

Quick Start Guide

1

Visit https://friendli.ai/

2

Sign up for free trial

3

Get $10 credits automatically

4

Create API token from dashboard

5

Use with OpenAI SDK (change base_url)

Available Models

5 free models
Model Name ID Context Capabilities
GLM-5.1 Free
zai-org/GLM-5.1
- -
Gemma 4 31B Free
google/gemma-4-31B-it
262 000 Context
-
GLM 5.2 Free
zai-org/GLM-5.2
1 000 000 Context
-
GLM 5.3 Flash Free
zai-org/GLM-5.3-Flash
1 000 000 Context
-
GLM 5.3 Free
zai-org/GLM-5.3
1 000 000 Context
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_FRIENDLI_KEY",
    base_url="https://inference.friendli.ai/v1"
)

response = client.chat.completions.create(
    model="zai-org/GLM-5.1",
    messages=[
        {"role": "user", "content": "What makes your inference fast?"}
    ]
)

print(response.choices[0].message.content)

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Tier 0: adaptive (60 Requests per minute from Tier 1)

Daily Quota

Requests per day

Credit-based

Token Limit

Tokens per minute

Varies by model

Monthly Quota

Per month limit

One-time trial

Free Credits

One-time

Trial credits at onboarding (amount not published)

Use Cases

Evaluating inference latency

Enterprise AI prototyping

Low-latency chatbots

Batch processing tasks

Limitations & Considerations

$10 credit is one-time trial

Billing required after credits

Limited model selection

Enterprise-focused pricing

Credit card required for continued use

Community Hub

Live

Join the discussion, share tips, and rate Friendli AI.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using Friendli AI

Start Building Now