Skip to content

CoolApiStuff/Free_Proxy_API_LLMs

Repository files navigation

AI Model Comparison

This document provides a comparative analysis of the free and premium offerings of various AI models, including ConvoAI, ShuttleAI, QuantumAI, ElectronHub, Fresed, Webraft, AnyAI, ShadowJourney, Pawan.KRD, ZuckiJourney, OxyAPI, NagaAI, Visioncraft, and GPT4ALL. The information presented here is compiled and reformulated from the official documentation of each respective API.

Disclaimer: I am not affiliated with any of the APIs mentioned in this document. While I have made an effort to include only reputable services, it is important to note that some actors in the AI API space may be malicious. Always exercise caution when using third-party APIs and ensure you understand their terms of service and privacy policies. Feel free to use discussion for any review, informations, correction or update.

For the most up-to-date and comprehensive information on free and freemium AI APIs, please refer to the following resources:

These repositories offer complementary information and may include additional services not covered in this comparison.

Table 1: Comparison of Free Offers

Model Daily Requests Rate Limit (requests/min) Key Features Restrictions
ConvoAI 1,000 60 Access to basic models, limited premium model access Lower request limits, slower response speed, no NSFW content
ShuttleAI 500 5 Access to limited models Limited model selection, lower API call limits
QuantumAI 850 10 Access to limited models Limited model selection, lower request limits
ElectronHub 500 5 Access to basic models, limited advanced features Limited daily credits, basic support, limited rate limit
Fresed 100 (Request Mode) or 80,000 tokens (Token Mode) No limit in Token Mode Access to various models, including GPT-4 (limited), two limit modes Limited daily tokens, Claude access requires subscription
Webraft 500 60 Access to a wide range of text and image models Limited model selection, daily credit limit
AnyAI Varies by model (see AnyAI/models.md) Varies by model Access to open-source LLMs, limited access to closed-source LLMs, DALL-E 3, GlobalAsk, Imagine, Vision Limited access to closed-source LLMs, character limit per message
ShadowJourney 2500 credits 15 Access to most models, limited roleplay Daily credit limit, restricted roleplay
Pawan.KRD Unlimited for CosmosRP and CosmosRP-IT, limited for others 3 Access to CosmosRP and CosmosRP-IT, unlimited usage for these models IP lock, limited access to other models
ZuckiJourney 22,500 4 (/unf/) or 12 (/v1/) Access to all models, IP-locked key Limited daily tokens, lower support priority
OxyAPI Varies by model (see OxyAPI/models.md) Varies by model Access to a limited selection of models Limited model selection, lower request limits
NagaAI Varies by model (see NagaAI/models.md) Varies by model Access to a limited selection of models Limited model selection, lower request limits
Visioncraft Limited (see Visioncraft Limits) Increased (Tier 1) / Unlimited (Tier 2) Access to all models, including LLMs and Stable Diffusion models Limited requests per second in the free tier
GPT4ALL Varies by endpoint (see GPT4ALL/Table pricing & limit.md) Varies by endpoint Access to a limited set of LLMs and image generation models Limited monthly balance, lower rate limits

Table 2: Comparison of Premium Offers

Model Pricing Tiers Additional Features Scalability Options
ConvoAI Premium ($4.99/month), Professional ($9.99/month), Enterprise ($19.99/month) Access to all models, increased request limits, faster response speed, NSFW content, dedicated servers (Enterprise) Higher request limits, faster response speed, dedicated servers (Enterprise)
ShuttleAI Pro ($9.99/month), Business ($19.99/month), Enterprise ($49.99/month) Access to premium models, higher API call limits, private community, priority support, beta access, dedicated servers Higher API call limits, dedicated servers
QuantumAI Pro (monthly, lifetime, yearly), Enterprise (custom pricing) Early access to models, higher rate limits, access to all models, custom plans Higher rate limits, custom plans
ElectronHub Starter ($5/month), Pro ($29/month), Business ($49/month) Increased daily credits, priority support, higher rate limits, access to advanced features, early access to new models, hands-on coding assistance (Business) Higher daily credits, higher rate limits
Fresed Claude access ($3/month), Unlimited access ($100/month), Donations (tokens/month) Unlimited tokens ($100/month), Claude access, unlimited GPT-4 requests ($100/month), no request limit in Token Mode Unlimited tokens, unlimited GPT-4 requests
Webraft Basic (€3/month), Medium (€6/month), Pro (€10/month), Ultra (€17.50/month), Ultra Pro Max (€27.50/month), Rich (€58/month) Increased daily credits, non-replenishing credits, access to exclusive models, early access to new models and services, Discord perks, discounted hostings, private endpoints (higher tiers), dedicated server (highest tier) Increased daily credits, private endpoints, dedicated server
AnyAI Premium (pricing not specified) Increased access to closed-source LLMs, increased character limit per message Increased access to closed-source LLMs
ShadowJourney Premium (pricing not specified) Unlimited credits, no request limit, access to all models including premium ones, allowed roleplay Unlimited credits, no request limit
Pawan.KRD Supporter (donation-based) Access to all models, higher context sizes, increased daily API credits, higher rate limits, no IP lock, unlimited usage for CosmosRP-Pro and CosmosRP-Pro-IT (Supporter I and above) Higher context sizes, increased daily API credits, higher rate limits
ZuckiJourney Booster (free), Donator (one-time donation > $5), Subscriber (~$10/month), Enterprise ($100/month) Increased daily tokens, IP-free key (Subscriber and Enterprise), higher support priority Higher daily tokens, IP-free key
OxyAPI Basic ($5.99/month), Premium ($9.99/month), Professional ($16.99/month) Access to all 150+ models, higher request limits, full access to plugins, priority support Higher request limits
NagaAI Tier 1, Tier 2, Tier 3, Tier 4 (contact Naga for pricing) Access to all models, increased request limits, increased daily usage limits, faster response times, priority support Increased request limits, increased daily usage limits
Visioncraft Tier 1 ($10/month), Tier 2 ($20/month) Increased (Tier 1) / Unlimited (Tier 2) requests per second, priority support Increased/unlimited requests per second
GPT4ALL Tier 1 ($5/month), Tier 2 ($8/month), Tier 3 ($12/month), Tier 4 ($16/month), Tier 5 ($20/month), Tier 6 ($24/month) Access to all models, increased monthly balance or unlimited usage, higher rate limits Increased monthly balance, unlimited usage, higher rate limits

Releases

No releases published

Packages

No packages published