Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Description

Chat Stream offers users the opportunity to tap into two robust language models developed by DeepSeek, showcasing their impressive capabilities. The models, DeepSeek V3 and R1, contain a staggering 671 billion parameters, with 37 billion activated per token, and consistently achieve remarkable benchmark performances, such as MMLU at 87.1% and BBH at 87.5%. With an extensive context window length of 128K, these models excel in tasks like code generation, complex mathematical computations, and processing multiple languages. Technically, they leverage an advanced Mixture-of-Experts (MoE) architecture, utilize Multi-head Latent Attention (MLA), feature auxiliary-loss-free load balancing, and implement a multi-token prediction objective to enhance performance. Deployment is versatile, providing a web-based chat interface for immediate access, easy integration into websites through iframes, and dedicated mobile applications for both iOS and Android devices. Furthermore, the models are compatible with various hardware, including NVIDIA, AMD GPUs, and Huawei Ascend NPUs, allowing for both local inference and cloud-based deployment. Users can benefit from different access methods, including free chat without the need for registration, website embedding options, mobile app usage, and a premium subscription that offers an ad-free experience, ensuring flexibility and accessibility for all.

Description

UncensoredLLM serves as a comprehensive API gateway compatible with OpenAI, designed for utilizing uncensored, modified, and roleplay-optimized language models. Developers have the flexibility to choose models by their unique IDs and integrate them seamlessly into their applications, whether through code or compatible chat, writing, and coding clients, utilizing a straightforward base URL and API key for access. The extensive catalog features various builds from model families, including DeepSeek, GLM, Qwen, Gemma, Kimi, and Llama, each with distinct input and output token pricing structures. Additionally, the same API key grants users access to endpoints for generating images and videos, with costs incurred per image or per second of video. Users are billed based on a prepaid balance, and there's a browser-based playground that allows a limited number of free interactions with selected models each day. Publicly available model pages provide insights into catalog details and pricing, while each model undergoes a daily fixed-prompt verification process to ensure accuracy in reported input-token usage, enhancing the reliability of the service. This systematic approach not only improves transparency but also builds user trust in the platform’s capabilities.

API Access

Has API No 

API Access

Has API Yes 

Screenshots View All

No images available

Screenshots View All

No images available

Integrations

Claude Code No 
Cline No 
Cursor No 
DeepSeek R1 Yes 
DeepSeek-V3 Yes 
Janitor AI No 
LiteLLM No 
Novelcrafter No 
Open WebUI No 
OpenCode No 
SillyTavern No 
n8n No 

Integrations

Claude Code Yes 
Cline Yes 
Cursor Yes 
DeepSeek R1 No 
DeepSeek-V3 No 
Janitor AI Yes 
LiteLLM Yes 
Novelcrafter Yes 
Open WebUI Yes 
OpenCode Yes 
SillyTavern Yes 
n8n Yes 

Pricing Details

No price information available.
Free Trial No 
Free Version Yes 

Pricing Details

$10 one-time
API usage is metered by model, with separate input and output token rates; image generation is priced per image, and video generation per second. Prepaid top-ups start at $10, with no subscription required and balances that do not expire. Top-ups earn 5% bonus credit from $200, 10% from $500, and 15% from $1,000. A browser playground offers a limited number of free daily turns on selected language models; API and media usage draw on prepaid credit.
Free Trial No 
Free Version Yes 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Customer Support

Business Hours Yes 
Live Rep (24/7) No 
Online Support No 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Types of Training

Training Docs No 
Webinars No 
Live Training (Online) No 
In Person No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Vendor Details

Company Name

Chat Stream

Founded

2023

Country

Hong Kong

Website

www.chatstream.org

Vendor Details

Company Name

Uplink Switch LLC

Founded

2026

Country

United States

Website

uncensoredllm.ai

Product Features

Product Features

Alternatives

Qwen2.5-Max Reviews

Qwen2.5-Max

Alibaba

Alternatives

DeepSeek-V2 Reviews

DeepSeek-V2

DeepSeek
Hy4 Reviews

Hy4

Tencent
Grokified Reviews

Grokified

DEEPORAX AI
DeepSeek R1 Reviews

DeepSeek R1

DeepSeek