Cheapest GPT-5.4-class model for simple high-volume tasks.阅读更多 →
Gemini 2.5 Pro1 FREE
Gemini 2.5 Pro by Google is a powerful AI model that can handle complex tasks and provide detailed answers.阅读更多 →
Gemini 3.1 Flash Lite1 FREE
Gemini 3.1 Flash Lite — Google's most cost-efficient model, optimized for high-volume agentic tasks, translation, and simple data processing. 1M-token context.阅读更多 →
Qwen Plus1 FREE
Alibaba Qwen Plus — best balance of cost, quality, and speed. Strong reasoning and multilingual coverage. 131K token context.阅读更多 →
Qwen Turbo1 FREE
Alibaba Qwen Turbo — fastest and cheapest in the Qwen line. Solid for quick chat, classification, and short-form content. 1M token context.阅读更多 →
Qwen3 Coder Plus1 FREE
Alibaba Qwen3 Coder Plus — coding-specialized variant. Strong at code generation, refactoring, and tool-use. 1M token context.阅读更多 →
Claude 4.5 Haiku2 FREE
A model from Anthropic that is their most affordable offering.阅读更多 →
DeepSeek V4 Flash2 FREE
DeepSeek V4 Flash — fast, cheap, with built-in thinking mode. 1M-token context, up to 384K output. Drop-in successor to deepseek-chat / deepseek-reasoner.阅读更多 →
GPT 5.4 Mini2 FREE
Strongest mini model for coding, computer use, and subagents.阅读更多 →
Grok 4.32 FREE
The latest and most intelligent model from xAI. Tops leaderboards in agentic tool calling and instruction following. 1M token context.阅读更多 →
Qwen Max2 FREE
Alibaba Qwen Max — flagship reasoning model. Top performance for complex tasks, deep analysis, and structured output. 32K token context.阅读更多 →
Qwen VL Max2 FREE
Alibaba Qwen VL Max — multimodal flagship. Accepts images alongside text, returns text. Use it for visual Q&A, OCR, and image-grounded reasoning.阅读更多 →
DeepSeek V4 Pro3 FREE
DeepSeek V4 Pro — flagship reasoning model with deeper thinking, stronger tool use, and higher quality output. 1M-token context, up to 384K output. Currently 75% off through 2026-05-31.阅读更多 →
Best intelligence at scale for agentic, coding, and professional workflows.阅读更多 →
Gemini 3.5 Flash3 FREE
Gemini 3.5 Flash — Google's frontier-intelligence model tuned for speed with superior search and grounding. Excellent for agentic loops, long-horizon coding, and rapid iteration. 1M-token context.阅读更多 →
Claude 4.5 Sonnet4 FREE
The most popular model from Anthropic has a great personality.阅读更多 →
Gemini 3 Flash Preview4 FREE
Gemini 3 Flash Preview by Google is the quickest and cheapest model for thinking.阅读更多 →
Gemini 3.1 Pro Preview4 FREE
Latest Gemini Pro model from Google with improved reasoning capabilities.阅读更多 →
吐槽长度
较长的吐槽费用更高。一句话:1×,短:10×,中:15×,长:20×,加长:24× 基础费用。
一句话(约 10 个词)3 FREE
短(约 250 词)30 FREE
中等(约 500 字)45 FREE
长(约 1000 字)60 FREE
扩展版(约 1500 字)72 FREE
吐槽强度
吐槽的力度。
Mild
Gentle pokes — soft, mostly harmless ribbing.
Medium
A balanced roast that lands without drawing blood.