Use LongCat 2.0 in Tabbit
Use in Tabbit LongCat 2.0
Featured prompts
LongCat-2.0 API Platform Quick Start (Official Quick Start + Chat Completions Reference + Pricing)
One-sentence takeaway This official documentation gets you an API key in five minutes, lets you connect LongCat-2.0 to any client using either OpenAI- or Anthropic-compatible formats, and explains the 1M context / 128K maximum output parameters and the pricing。
LongCat-2.0 Chat Template and Tool-Calling Configuration (Official Hugging Face Model Card)
One-sentence takeaway The model card provides directly reusable chat-template invocation examples: how to enable or disable thinking mode (enablethinking / savereasoningcontent), the function-calling format (arguments must be a dict rather than a string), and 。
Hermes Agent Integration with LongCat-2.0 (Official Documentation + Nous Portal Free Entry)
One-sentence takeaway Two commands connect Hermes Agent (Nous Research's open-source terminal Agent) to LongCat-2.0, and the official source offered a free one-week trial on Nous Portal, making it suitable for trying long-running Agents with a 1M context at no。
Claude Code Integration with LongCat-2.0 (Official Documentation)
One-sentence takeaway By rewriting the environment variables in ~/.claude/settings.json, you can point all four Claude Code model slots (primary model / small fast model / Sonnet / Opus) to LongCat-2.0's Anthropic-compatible endpoint, allowing Claude Code to u。
OpenClaw Integration with LongCat-2.0 (Official Documentation)
One-sentence takeaway Registering a custom provider in OpenClaw's ~/.openclaw/openclaw.json lets you switch the default model to LongCat-2.0; the context-window and maximum-output settings given by the official source (1048576 / 131072) can be copied directly.。
OpenCode LongCat-2.0 Configuration (Official Documentation + Free Access)
One-sentence takeaway With opencode auth login and an opencode.json file, OpenCode can use LongCat-2.0. The official announcement says the model is available for free on OpenCode; the same page also explains how to toggle LongCat's thinking mode in OpenCode.。
Reviews and field notes
LongCat-2.0 Official Model Card: Specifications and Official Benchmarks (Including Comparison Tables with Gemini/GPT-5.5/Claude Opus)
One-sentence takeaway The official model card is the primary authoritative source for judging LongCat-2.0's suitable tasks: it scores 59.5 on SWE-bench Pro, ahead of GPT-5.5 (58.6) and Gemini 3.1 Pro (54.2), and reaches 70.8 on Terminal-Bench 2.1. However, it 。
LongCat-2.0 Official Technical Blog: Architecture, Training on Domestic Compute, and Inference Deployment (Release Notes)
One-sentence takeaway The official technical blog provides the complete technical foundation for LongCat-2.0 (LSA sparse attention, N-gram Embedding, 6D parallel training on domestic compute, and prefill-decode disaggregated deployment), making it useful for a。
OpenRouter Channel Data: LongCat-2.0 Pricing, Measured Performance, and Third-Party Benchmarks (Artificial Analysis)
One-sentence takeaway The OpenRouter page provides a third-party view beyond the official figures: LongCat-2.0 is listed at $0.30/$1.20 per 1M tokens (with a 60% discount at collection time), while the actual weighted transaction price for input was only $0.03。
AI Profit Boardroom field test: LongCat 2.0 game-building test and same-task comparison with GLM 5.2
One-sentence takeaway The author's test reached a conclusion opposite to most community sentiment: LongCat 2.0's games were "playable but rough and buggy" (one build even showed a completely black screen), while GLM 5.2's outputs on the same tasks were "cleane。
BenchLM comparison page: GPT-5.5 vs LongCat-2.0 — a boundary note on "no shared benchmarks, no quality verdict"
One-sentence takeaway As of 2026-08-17, BenchLM found no shared third-party benchmark results between GPT-5.5 and LongCat-2.0 (38 for GPT-5.5 and 0 for LongCat-2.0), so "the public evidence does not support any quality verdict." This is an authoritative bounda。
LongCat
Use LongCat 2.0 in Tabbit
Explore sourced prompt guides, evaluations, and community reports for LongCat 2.0—then use the model directly in Tabbit.