Chub AI is a platform for character cards, lorebooks, and AI roleplay. Explore model usage, compare GPTProto and OpenRouter API prices, and try models for your own character chat app.
Usage stats for Chub AI — most of the numbers come from OpenRouter and GPTProto together. Switch between weekly and daily to see how the mix shifts.
Token volumes mix OpenRouter (openrouter.ai/
See which models process the most reported Chub AI tokens on OpenRouter. Compare API rates for the same model version, then test how each model handles your character’s voice and story details.
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% | 56.9B |
2.  GLM 5.3Z-AI | $1.26 / $3.96$0.23 Cache read · per 1M tokens | −10% | −15% | 13.8B |
3.  Claude Sonnet 5.5Claude | $1.80 / $9.00$0.18 Cache read · per 1M tokens | −10% | −15% | 7.1B |
4. GLM 5.3 FlashZ-AI | $0.15 / $0.50$0.03 Cache read · per 1M tokens | — | −5% | 3.6B |
5. Claude Opus 5.5Claude | $3.60 / $18.00$0.18 Cache read · per 1M tokens | −10% | −15% | 3.6B |
6.  Gemini 3.7 FlashGoogle | $0.90 / $4.50$0.09 Cache read · per 1M tokens | −40% | −43% | 2.9B |
7. Gemini 3.8 FlashGoogle | $0.90 / $4.50$0.09 Cache read · per 1M tokens | −40% | −43% | 2.4B |
8.  Grok 4.6Grok | $1.20 / $3.60$0.30 Cache read · per 1M tokens | −40% | −43% | 1.8B |
9. Grok 4.7Grok | $1.20 / $3.60$0.30 Cache read · per 1M tokens | −40% | −43% | 700M |
10.  GPT 6 LunaOpenAI | $0.080 / $0.40$0.01 Cache read · per 1M tokens | −20% | −24% | 463M |
11. GPT 6.1 SolOpenAI | $1.60 / $8.00$0.08 Cache read · per 1M tokens | −20% | −24% | 107M |
Choose a model, enter your monthly token usage, and set the input share. Compare estimated costs on GPTProto, OpenRouter, and the direct provider for the same workload.
從切換模型、處理備援，到生成圖片和影片，人們使用 GPTProto 進行各種不同的工作。以下是他們選擇分享的內容。
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 to compare models and run your character chat app. API usage is charged at each model’s current rate, with no required monthly subscription.
立即開始。非常適合測試端點與試用新模型。隨時儲值 $20 以上即可解鎖贈送額度。
適合個人開發，以及準備上線的小型專案。
只要支付 $500，就能獲得 $600 餘額——贈送額度可疊加在已折扣的模型定價之上。專為執行正式生產工作負載的團隊打造。
Learn how models, character cards, lore, and conversation history work together in your own roleplay app.
Yes. GPTProto’s model APIs can generate character replies for your own app. Your frontend handles the chat interface, while your application manages characters, accounts, and conversation data. Start with a small prototype; our API guide covers model choices and integration.
A no-code builder can work if it supports authenticated API calls, secure server-side key storage, and conversation data. Check its support for streaming and the character features you need. For a first character prototype, follow our AI character API tutorial.
Yes, if your app supports their formats and prompting rules. It reads the character fields, selects relevant lorebook entries, and includes that text in the model request. GPTProto generates the reply; your app manages card imports, lore triggers, and token budgets. Test the assembled prompt to check what reaches the model.
Compare the same character, scene, and relevant lore across a few models available in the GPTProto catalog. Check voice, story consistency, response time, and cost. You can access multiple models with one key; use each model’s documented ID and request format. Treat usage rankings as a shortlist for testing.
Keep conversation history and character data in your application. Include recent dialogue and relevant earlier events in each request, using summaries when older messages no longer fit. Lorebooks can supply world facts; conversation summaries preserve what happened in a particular chat. Your app decides what context to send.
Measure input and output tokens per reply, then multiply by your expected monthly reply volume and the model’s rates. Input can include character details, lore, and earlier dialogue. Count regenerated replies and model-generated summaries too. Use the calculator to compare the same workload across providers, then refine the budget with actual usage.
Yes, by storing branches in your app and sending the selected branch’s history when requesting a reply. Your interface decides how users switch paths and which replies to keep. Generating another reply is an additional API call; opening a branch you have already saved does not require generating it again.
Yes, where the chosen model and endpoint support streaming. Your interface can display incoming text progressively. Confirm support in the model documentation and test interrupted connections and cancellation before enabling streaming for your users.
GPTProto’s routing and automatic failover features help handle upstream disruptions. Your app also needs timeout handling, controlled retries, and limits on user activity. Test with your expected traffic, monitor errors and response times, and provide a retry option when a reply cannot be completed.
Content sent in API requests passes through GPTProto to the selected model provider. Our Privacy Policy explains processing, short-term content retention, and metadata logging; provider policies also apply. Discuss any enterprise retention or routing requirements with our team before deploying sensitive workloads.
比較模型、了解 API 設定，以及圖像和影片在實際專案裡的做法。
Test your character prompts, compare API prices, and build with GPTProto’s model APIs. Access multiple chat models with one key, start with a small balance, and pay for the calls your app makes.
