Phala

AI inference provider available on Antbase

OpenAI-compatible

About Phala

Phala 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

Intelligence Score
43.0
Total Requests
71
Success Rate
8592.0%
Avg Latency
20590ms
Models
11
Tokens Processed
878.1K

Phala Models on Antbase

ModelScoreRequestsSuccess RateAvg Latencyp95 LatencyCapabilities
Anthropic: Claude Sonnet 4.660.0110000.0%2768ms2768ms
Anthropic: Claude Opus 559.0110000.0%2889ms2889ms
Anthropic: Claude Opus 4.656.0110000.0%4698ms4698ms
DeepSeek: DeepSeek V4 Flash53.02810000.0%6280ms13746ms
Phala: Qwen3.8 27B Uncensored (Aggressive)45.01310000.0%170459ms700624ms
🧠
Phala: Qwen3.6 35B A3B Uncensored (Aggressive)45.01110000.0%18885ms83040ms
🧠
Phala: Gemma 4 26B A4B Uncensored (Heretic)41.078571.0%9178ms35555ms
DeepSeek: DeepSeek V4 Flash 073130.020.0%2418ms2514ms
Anthropic: Claude Opus 4.729.030.0%2120ms3141ms
XAI: Grok 4.1 Fast28.010.0%3704ms3704ms
Anthropic: Claude Haiku 4.526.030.0%3096ms4753ms

How to Use Phala on Antbase

All Phala models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Phala 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 Phala if optimal)
response = client.chat.completions.create(
    model="ant:auto",
    messages=[{"role": "user", "content": "Hello!"}],
)

Why Use Phala Through Antbase?

  • •No separate account needed — access Phala models instantly through your Antbase API key.
  • •Intelligent routing — ANT automatically selects the best Phala model for each task, or falls over to another provider if Phala is slow or down.
  • •Same token prices — Antbase charges zero markup on Phala token prices. You pay exactly what Phala charges.
  • •Automatic failover — if Phala has an outage, your requests seamlessly route to an equivalent model on another provider.