🤖 ArliAI

Derestricted models & image generation — uncensored variants with 54+ models

🤖

ArliAI

Speed: ⚡ 16 tok/s avg
Models: 54
Price: $10+/mo
Status: ✅ Online
Avg Speed
16 tok/s
Models
54
Price
$10+/mo
Best For
Derestricted & Image Gen

💰 Plan & Pricing

ℹ️
From $10/mo
Derestricted/uncensored model variants. Also provides image generation API.

🔑 API Key

44c327...cdff9

🌐 Endpoint

https://api.arliai.com/v1/chat/completions

📦 Models (54 total — derestricted)

ModelSpeedCategoryNotes
deepseek-r1-0528⚡ 16 tok/sReasoning🔥 Derestricted R1
qwen3-235b⚡ 15 tok/sChat/CodingDerestricted Qwen3
llama-4-maverick⚡ 14 tok/sChatDerestricted Llama 4
meta-llama/llama-3.1-70b-instruct⚡ 16 tok/sChatDerestricted Llama
meta-llama/llama-3.1-8b-instruct⚡ 18 tok/sChatSmall derestricted Llama
mistralai/mistral-7b-instruct⚡ 17 tok/sChatDerestricted Mistral
deepseek-v3⚡ 14 tok/sChatDerestricted DS-V3
qwen2.5-coder-32b-instruct⚡ 15 tok/sCodingDerestricted Qwen Coder
various fine-tunes⚡ variesChat/CodingMany community fine-tunes

🔥 Image Generation API also available — + ~45 more derestricted model variants

⚠️ Speed Note

⚠️
16 tok/s average — ArliAI is significantly slower than other providers. All models average ~16 tok/s with occasional spikes. Best for derestricted/uncensored access when speed is not critical.
curl -X POST https://api.arliai.com/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.1-70b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

🐍 Python Example

from openai import OpenAI

client = OpenAI(
    api_key="44c327...cdff9",
    base_url="https://api.arliai.com/v1"
)

response = client.chat.completions.create(
    model="meta-llama/llama-3.1-70b-instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

⚠️ Pitfalls & Notes

ℹ️
Offers derestricted/uncensored model variants — ArliAI provides uncensored versions of popular models for unrestricted chat.
ℹ️
Has image generation endpoint — ArliAI also offers an image generation API alongside text completions.
⚠️
16 tok/s is slower than most providers — Average speed is below the typical range; expect longer response times on large outputs.
ℹ️
54+ models with uncensored chat and image gen — Wide model selection covering both text and image generation use cases.

🏷️ Categories

Chat Image Gen Uncensored