Sophia’s LoreBary connects roleplay tools with AI providers and adds characters, lorebooks, and plugins to your chats. Explore its publicly reported model usage, compare API prices, and try roleplay models on GPTProto.
See how model usage changes over time, based on LoreBary traffic reported by OpenRouter. Switch between daily and weekly views to explore the model mix.
Token volumes mix OpenRouter (openrouter.ai/
Explore the models with the most reported LoreBary usage. Compare GPTProto’s prices with the direct provider and OpenRouter, then test the models available here for your own chats or a similar app.
Live GPTProto prices for each model, next to what it would cost elsewhere.
| Model | Price: GPTProto | vs Official | vs OpenRouter | Tokens |
|---|---|---|---|---|
1.  DeepSeek FlashDeepSeek | $0.30 / $1.20$0.01 Cache read · per 1M tokens | — | −5% | 43.3B |
2.  GLM 5.3Z-AI | $1.26 / $3.96$0.23 Cache read · per 1M tokens | −10% | −15% | 28.7B |
3.  Gemini 3.8 FlashGoogle | $0.90 / $4.50$0.09 Cache read · per 1M tokens | −40% | −43% | 22.7B |
4. GLM 5.3 FlashZ-AI | $0.15 / $0.50$0.03 Cache read · per 1M tokens | — | −5% | 8.3B |
5. Gemini 3.7 FlashGoogle | $0.90 / $4.50$0.09 Cache read · per 1M tokens | −40% | −43% | 3.9B |
6.  Grok 4.6Grok | $1.20 / $3.60$0.30 Cache read · per 1M tokens | −40% | −43% | 3.1B |
7. Gemini 3.5 Flash LiteGoogle | $0.18 / $1.50$0.02 Cache read · per 1M tokens | −40% | −43% | 1.5B |
8.  Claude Opus 5.5Claude | $3.60 / $18.00$0.18 Cache read · per 1M tokens | −10% | −15% | 1.2B |
9.  GPT 6 LunaOpenAI | $0.080 / $0.40$0.01 Cache read · per 1M tokens | −20% | −24% | 1.2B |
10. Grok 4.7Grok | $1.20 / $3.60$0.30 Cache read · per 1M tokens | −40% | −43% | 1.1B |
11. Claude Sonnet 5.5Claude | $1.80 / $9.00$0.18 Cache read · per 1M tokens | −10% | −15% | 313M |
12. GPT 6.1 SolOpenAI | $1.60 / $8.00$0.08 Cache read · per 1M tokens | −20% | −24% | 189M |
Building your own character chat? Explore our Roleplay API setup and model comparison.
Choose a model, enter your monthly token usage, and set the share of input tokens. Compare estimated costs on GPTProto, OpenRouter, and the direct provider for the same workload.
Read user feedback on model access, API setup, and creative workflows.
For a team already juggling DeepSeek, Kimi, Qwen, or other providers, a shared routing layer can be reasonable if it removes duplicated work and the fallback behavior is tested. GPTProto is one implementation of this approach.
I've been testing GPTProto recently, and it's honestly made my creative workflow much simpler. Instead of paying for multiple subscriptions, I can access several leading AI models from one place.
I turned this single prompt into a cinematic fantasy video using GPTProto. "Continuous 15-second cinematic shot, 4K resolution, hyper-realistic dark fantasy photorealism…"
I challenged myself to create a cinematic AI cooking short in just 15 seconds. I used GPTProto to bring the entire workflow together, from image generation to video, all in one place.
Made with Seedance 2.0 + GPT Image 2 on GPTProto. A Pixar-style commercial with the perfect glow.
What worked for me was pointing the cloud connections at GPTProto so the frontend only sees one endpoint and I just change the model name to swap. I am not rebuilding a connection from scratch every time.
I route the calls through GPTProto so a fallback is a config switch instead of a weekend rewrite when a model disappears. It turns "my default model just got export controlled" from an incident into a config change.
I used to switch between different AI tools just to compare results. Now I just use GPTProto. GPT-5, Claude, Gemini, Kimi, and more — all in one workspace.
I route the calls through GPTProto so the model id and latency land in one place regardless of which provider is behind it. The win is having the log schema consistent across providers.
I created this 15-second cinematic product video with GPTProto using Seedance 2.0, and I was really impressed by how smooth the workflow was.
GPTProto routes the character prompt and shot list to a top model on one API key: 20 minutes … voices it and burns in captions from the same key: 20 minutes.
Text, images, and voice are configured separately. You can keep OpenRouter for text and use GPTProto for visuals.
The call layer underneath the router is GPTProto, so swapping a model does not require provisioning a new provider integration. Changing models becomes cheap enough that the question stops being "should we change."
Use one GPTProto balance across available models. Start with a small top-up for testing, or add more credit for ongoing API usage. Each model is billed at its current rate.
시작해 보세요. 엔드포인트를 테스트하고 새로운 모델을 시험해 보기에 좋습니다. 언제든 $20 이상 충전하면 보너스 크레딧을 받을 수 있습니다.
개인 개발과 프로덕션에 올리는 작은 프로젝트에 맞는 균형입니다.
$500로 $600 잔액을 받을 수 있으며, 보너스 크레딧은 이미 할인된 모델 가격 위에 추가로 쌓입니다. 프로덕션 워크로드를 운영하는 팀을 위해 설계되었습니다.
Understand the usage data, compare model access, and plan your next roleplay setup.
Sophia’s LoreBary is a free AI roleplay platform and toolkit. It connects compatible chat tools to AI providers and adds characters, lorebooks, plugins, and other roleplay content to requests. GPTProto provides API access to models you can evaluate for your roleplay workflows.
The ranking shows models receiving traffic attributed to LoreBary on OpenRouter during the displayed period. It is based on reported token usage, which can change as people switch models. Other providers and traffic outside OpenRouter are not included in these figures.
Use the ranking as a shortlist. Test whether each model follows your character’s voice, remembers the details included in the request, and moves the scene forward. Compare response speed and cost with your own prompts; popularity alone does not decide which model fits your story.
LoreBary offers custom proxy endpoints for providers outside its built-in options. A setup needs the provider endpoint, API key, and model ID. To evaluate GPTProto for that route, use its documented Chat Completions endpoint and an available model, then verify a reply through your chosen frontend before moving an existing chat.
GPTProto offers discounted rates on selected models. For models available on both platforms, compare the same version’s input and output prices in the table. The calculator estimates the difference for your token usage. Token rates, top-up fees, and bonus credits are separate parts of the comparison.
Cost depends on the model, the input sent with each turn, and the length of its replies. Character cards, lorebooks, commands, and previous messages can all add input tokens. Use your measured token usage for a better estimate; long conversations can cost more than their visible message count suggests.
Yes. GPTProto can provide model access for the AI replies. Your app manages the interface, characters, lorebook retrieval, conversation history, and user accounts. Start with a small prototype and compare models using the same scenes. Our Roleplay API guide covers model access, testing, and cost comparison.
GPTProto’s routing and failover features help handle upstream issues. Before scaling your app, test the models and routes you plan to use, including streaming, rate limits, and retry behavior. Monitor response times and errors in your production workflow.
Check LoreBary’s official status page for service updates. If a request fails, also check your provider’s status, API configuration, and remaining credit. The usage chart on this page shows historical activity, not live service availability.
GPTProto’s Privacy Policy explains processing, short-term content retention for delivery and debugging, and limited metadata logging. Model-provider policies also apply to forwarded requests. For enterprise requirements, confirm retention and provider terms with our team before deployment.
모델 비교, API 설정, 이미지와 영상 작업 흐름을 정리했습니다.
For your own app or a compatible chat frontend, test the models you need through one GPTProto API key. Compare current rates and start with a small prepaid balance.
