LongCat API Platform Change Log ​

Version: 2026-06-30 ​

LongCat-2.0 Release & Billing Now Available ​

  • LongCat-2.0's core features include:

    • Trillion Parameters, 1M Long Context: Native tool calling and multi-step reasoning, reliably supporting long-context agent tasks.

    • Superior Coding Capability: Excels in code generation, code understanding, and automated programming tasks.

    • Deeply Compatible with Claude Code and Other Mainstream Dev Environments：Works efficiently with Claude Code, Hermes, OpenClaw, OpenCode and Kilo Code.

  • LongCat API Platform — Billing Now Available

    • Token Pack: Purchase a fixed Token quota upfront, valid for 30 calendar days from the date of purchase. Ideal for short-term, high-volume usage.

    • API Pay-As-You-Go: Top up your balance and get charged based on actual Token consumption. Perfect for variable workloads or teams looking to keep costs under tight control.

  • For calling instructions, please refer to: LongCat API Platform Interface Documentation.

Version: 2026-05-29 ​

LongCat Model Service Sunset ​

  • Since the launch of LongCat-2.0-Preview, we have seen an overwhelming response from users, and demand for service resources continues to grow. To consolidate resources and better support the testing and iteration of LongCat-2.0-Preview, we will be retiring the legacy models. Effective May 29, 2026, the platform will retire the following 6 models:

    • LongCat-Flash-Chat

    • LongCat-Flash-Thinking

    • LongCat-Flash-Thinking-2601

    • LongCat-Flash-Lite

    • LongCat-Flash-Omni-2603

    • LongCat-Flash-Chat-2602-Exp

  • Please migrate your models according to your needs.You are welcome to apply for access to LongCat-2.0-Preview — a limited number of beta slots are released daily at 09:00:00 and 21:00:00 (UTC+8), with availability expanding gradually. Spots are allocated on a first-come, first-served basis. Thank you for your understanding and continued support.

Version: 2026-04-20 ​

LongCat-2.0-Preview Release ​

  • LongCat-2.0-Preview's core features include:

    • Designed for Agent development, with native support for tool calling, multi-step reasoning, and long-context tasks;

    • Excelling in code generation, automation workflows, and complex instruction execution;

    • Deeply integrated with productivity tools like Claude Code, OpenClaw, OpenCode, and Kilo Code.

  • With an initial quota of 5,000,000 Tokens/day, you can submit model feedback. Each valid submission has a chance to earn a quota refresh, up to a daily maximum of 120,000,000 Tokens.

  • For calling instructions, please refer to: LongCat API Platform Interface Documentation.

Version: 2026-03-12 ​

LongCat-Flash-Thinking Upgrade ​

  • To ensure top-tier inference performance, the LongCat API Platform has upgraded the LongCat-Flash-Thinking model. All existing requests will be automatically routed to the latest version (LongCat-Flash-Thinking-2601) without requiring any code changes.

  • Effective Date: 2026-03-12 20:00:00 (UTC+8)

  • For calling instructions, please refer to: LongCat API Platform Interface Documentation

Version: 2026-03-11 ​

LongCat-Flash-Omni-2603 Release ​

  • LongCat-Flash-Omni-2603 is officially released. As an upgraded version of LongCat-Flash-Omni, it is an end-to-end Omni interaction model with more human‑like responsiveness and stronger full-modality perception capabilities. You can chat with it for free on LongCat Chat or call it by specifying model=LongCat-Flash-Omni-2603.

  • Key improvements over LongCat-Flash-Omni:

    • Natural dialogue flow via deep semantic alignment and personalized style adaptation.
    • Improved accuracy across multimodal tasks involving vision, speech, and text.
    • Enhanced performance in complex problem-solving, emotional understanding, and casual entertainment scenarios.
    • Support for native voice Function Calls, allowing for direct parsing of audio commands and real-time interaction with virtually zero latency.

  • For calling instructions, please refer to: LongCat API Platform Interface Documentation

Version: 2026-02-05 ​

LongCat-Flash-Lite Release ​

  • LongCat-Flash-Lite is officially released. Built on a highly efficient MoE architecture (68.5B total parameters, about 3B activated per inference), the model achieves superior parameter utilization through an N-gram embedding table, specifically optimized for inference efficiency and specialized use cases.
  • Compared to models of similar scale, the core features are as follows:
    • Superior Inference Efficiency: By mitigating I/O bottlenecks within MoE layers via the N-gram embedding table—combined with specialized cache and kernel optimizations—the model significantly reduces latency and boosts overall efficiency.
    • Strong Agentic and Coding Performance: Demonstrates exceptional competitiveness in tool-use and coding proficiency, delivering high-tier performance relative to its model scale.
  • For calling instructions, please refer to: LongCat API Platform Interface Documentation
  • Open-Source Platforms:

Version: 2026-01-14 ​

LongCat-Flash-Thinking-2601 Release ​

  • LongCat-Flash-Thinking-2601 is officially released. As an upgraded reasoning model, it is built on a Mixture-of-Experts (MoE) architecture with a total of 560 billion parameters. While maintaining strong competitiveness in traditional reasoning benchmarks, the model systematically enhances AI Agent reasoning capabilities through large-scale multi-environment reinforcement learning.

  • Compared to the LongCat-Flash-Thinking model, the core features of this upgrade are as follows:

    • Extreme Robustness in Noisy Environments: Through systematic curriculum training focused on noise and uncertainty in real-world environments, the model delivers exceptional performance in agent tool calling, agent search, and tool-fusion reasoning, with a significant boost in generalization capabilities.
    • Powerful Agent Capabilities: By constructing environment dependency maps with over 60 types of tools, combined with multi-environment expansion and large-scale exploration training, the model significantly improves generalization in complex, out-of-distribution (OOD) real-world scenarios.
    • Advanced Deep Thinking Mode: Utilizing parallel reasoning to expand thinking breadth, combined with a summarization mechanism featuring recursive feedback to expand thinking depth, effectively solving high-difficulty problems.

  • For calling instructions, please refer to: LongCat API Platform Interface Documentation

  • Open-Source Platforms:

Version: 2025-12-22 ​

LongCat-Flash-Chat Update ​

  • The LongCat-Flash-Chat model has been upgraded to a new version. This update involves model capability enhancements only. The model name and API invocation method remain unchanged.

  • Building upon its principles of “extreme efficiency” and “lightning-fast responsiveness,” the new version of LongCat-Flash-Chat further improves its context handling and programming capabilities:

    • Significantly enhanced programming performance: Deep optimizations for developer-oriented use cases, with substantial improvements in code generation, debugging, and code explanation tasks. Developers are encouraged to prioritize evaluation and testing.
    • Support for a 256K ultra-long context length: The context length has doubled compared to the previous generation (128K), enabling efficient processing of large documents and long-sequence tasks.
    • Comprehensively strengthened multilingual capabilities: High-quality support for nine languages, including Spanish, French, Arabic, Portuguese, Russian, and Indonesian.
    • More robust Agent capabilities: Improved stability and efficiency in complex tool invocation and multi-step task execution.

  • For API usage details, please refer to the LongCat API Platform Interface Documentation.

Version: 2025-09-22 ​

LongCat-Flash-Thinking Release ​

Version: 2025-09-05 ​

LongCat API Platform Launch ​

  • The LongCat API Platform is now live, supporting API calls to the LongCat-Flash-Chat model. You can call it by specifying model=LongCat-Flash-Chat.
  • For calling instructions, please refer to: LongCat API Platform Interface Documentation

Version: 2025-08-29 ​

LongCat-Flash-Chat Release ​