Friendli
AI inference provider available on Antbase
OpenAI-compatible
About Friendli
Friendli is an AI model provider accessible through Antbase. Use intelligent routing to automatically select the best model from this provider based on your task requirements.
Live Performance Data
Friendli Models on Antbase
| Model | Score | Requests | Success Rate | Avg Latency | p95 Latency | Capabilities |
|---|---|---|---|---|---|---|
| Llama 4 Scout 17B 16E Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Llama 4 Maverick 17B 128E Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 32B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 235B A22B Thinking 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| GLM 4.6 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Llama 3.3 70B Instruct | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| Llama 3.1 8B Instruct | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| Qwen3 30B A3B | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| Qwen3 235B A22B Instruct 2507 | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| MiniMax M2.1 | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| GLM 5 | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| MiniMax M2.5 | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| DeepSeek V3.2 | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| K EXAONE 236B A23B | 50.0 | 0 | 0.0% | 600ms | 1500ms | 🔧 |
| GLM 5.2 | 33.0 | 5 | 0.0% | 1129ms | 1185ms | 🔧 |
How to Use Friendli on Antbase
All Friendli models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Friendli model or let ANT's intelligent router automatically select the best model for your task.
python
from openai import OpenAI
client = OpenAI(
base_url="https://antbase.ai/v1",
api_key="your-ant-api-key",
)
# Let ANT auto-route (may use Friendli if optimal)
response = client.chat.completions.create(
model="ant:auto",
messages=[{"role": "user", "content": "Hello!"}],
)Why Use Friendli Through Antbase?
- •No separate account needed — access Friendli models instantly through your Antbase API key.
- •Intelligent routing — ANT automatically selects the best Friendli model for each task, or falls over to another provider if Friendli is slow or down.
- •Same token prices — Antbase charges zero markup on Friendli token prices. You pay exactly what Friendli charges.
- •Automatic failover — if Friendli has an outage, your requests seamlessly route to an equivalent model on another provider.