LongCat-2.0-FP8
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗DISCOVER & COMPARE
AIモデルを探す 17
LongCat-AudioDiT-1B
meituan-longcatLongCat-AudioDiT is a state-of-the-art (SOTA) diffusion-based text-to-speech (TTS) model that directly operates on the waveform latent space. > **Abstract**: We present LongCat-TTS, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as mel-spectrograms, the core innovation of LongCat-TTS lies in operating directly within the waveform latent space. This approach effectively mitigates compounding errors and drastically simplifies the TTS pipeline, requiring only a waveform variational autoencoder (Wav-VAE) and a diffusion backbone. Furthermore, we introduce two critical improvements to the inference process: first, we identify and rectify a long-standing training-inference mismatch; second, we replace traditional classifier-free guidance with adaptive projection guidance to elevate generation quality. Experimental results demonstrate that, despite the absence of complex multi-stage training pipelines or high-quality human-annotated datasets, LongCat-TTS achieves SOTA zero-shot voice cloning performance on the Seed benchmark while maintaining competitive intelligibility. Specifically, our largest variant, LongCat-TTS-3.5B, outperforms the previous SOTA model (Seed-TTS), improving the speaker similarity (SIM) scores from 0.809 to 0.818 on Seed-ZH, and from 0.776 to 0.797 on Seed-Hard. Finally, through comprehensive ablation studies and systematic analysis, we validate the effectiveness of our proposed modules. Notably, we investigate the interplay between the Wav-VAE and the TTS backbone, revealing the counterintuitive finding that superior reconstruction fidelity in the Wav-VAE does not necessarily lead to better overall TTS performance. Code and model weights are released to foster further research within the speech community. This repository provides the HuggingFace-compatible implementation, including model definition, weight conversion, and inference scripts. LongCat-AudioDiT obtains state-of-the-art (SOTA) voice cloning performance on the Seed-benchmark, surpassing both close-source and open-source modles.
翻訳待ち・原文を表示
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-AudioDiT-3.5B
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Chat
meituan-longcatWe introduce LongCat-Flash, a powerful and efficient language model with 560 billion total parameters, featuring an innovative Mixture-of-Experts (MoE) architecture. The model incorporates a dynamic computation mechanism that activates 18.6B∼31.3B parameters (averaging∼27B) based on contextual demands, optimizing both computational efficiency and performance. To achieve advanced training and inference efficiency, we employ a shortcut-connected architecture that expands computation-communication overlap window, achieving over 100 tokens per second (TPS) for inference cost-effectively. Our comprehensive training and scaling strategies ensure stable, efficient training, while tailored data strategies enhance model performance. Now we release LongCat-Flash-Chat, a non-thinking foundation model that delivers highly competitive performance among leading models, with exceptional strengths in agentic tasks. LongCat-Flash is designed and optimized under two key principles: efficient computation utilization, as well as efficient training and inference. Specifically, (1) As not all tokens are equal, we introduce the zero-computation experts mechanism in MoE blocks to allocate a dynamic computation budget to important tokens based on their significance, i.e., activating 18.6 to 31.3 billion parameters (out of 560 billion total) based on contextual demands. To ensure consistent computation load, we employ expert bias adjusted by a PID-controller, maintaining an average of∼27 billion activated parameters per token. (2) As communication overhead becomes a bottleneck during MoE model scaling, we incorporate the Shortcut-connected MoE (ScMoE) design to expand the computation-communication overlap window. Combined with customized infrastructure optimizations, this design enables training at a massive scale of over tens of thousands accelerators and inference with high throughput and low latency.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Lite
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Lite-FP8
meituan-longcatWe introduce LongCat-Flash-Lite, a non-thinking 68.5B parameter Mixture-of-Experts (MoE) model with approximately 3B activated parameters, supporting a 256k context length through the YaRN method. Building upon the LongCat-Flash architecture, LongCat-Flash-Lite distinguishes itself through the integration of an **N-gram embedding** table designed to enhance both model performance and inference speed. Despite allocating over 30B parameters to embeddings, LongCat-Flash-Lite not only outperforms parameter-equivalent MoE baselines but also demonstrates exceptional competitiveness against existing models of comparable scale, particularly in the agentic and coding domains. Through comprehensive scaling experiments across diverse scenarios, we identify specific regimes where embedding scaling achieves a superior Pareto frontier compared to increasing the number of experts, thereby offering a highly efficient alternative for model scaling. We further delineate a comprehensive set of architectural factors that determine embedding scaling efficacy, encompassing integration timing, parameter budgeting, hash collision mitigation, hyperparameter configuration, and embedding initialization, alongside the impacts of model width and depth. In contrast to FFN-based experts, the N-gram embedding table inherently mitigates I/O bottlenecks within MoE layers, yielding substantial improvements in inference latency. Furthermore, we introduce a specialized N-gram Cache and develop synchronized kernels, which collectively and significantly boost inference efficiency.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Lite-Sparse
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Omni
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Thinking
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Flash-Thinking-2601
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Image
meituan-longcatWe introduce **LongCat-Image**, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. > [!TIP] > Leveraging a stronger LLM for prompt refinement can further enhance image generation quality. Please refer to inference_t2i.py for detailed usage instructions. > [!CAUTION] > **📝 Special Handling for Text Rendering** > > For both Text-to-Image and Image Editing tasks involving text generation, **you must enclose the target text within single or double quotation marks** (both English '...' / "..." and Chinese ‘...’ / “...” styles are supported). > > **Reasoning:** The model utilizes a specialized **character-level encoding** strategy specifically for quoted content. Failure to use explicit quotation marks prevents this mechanism from triggering, which will severely compromise the text rendering capability.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Image-Dev
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 画像
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Image-Edit
meituan-longcatWe introduce **LongCat-Image-Edit**, the image editing version of Longcat-Image. LongCat-Image-Edit supports bilingual (Chinese-English) editing, achieves state-of-the-art performance among open-source image editing models, delivering leading instruction-following and image quality with superior visual consistency. - 🌟 **Superior Precise Editing**: LongCat-Image-Edit supports various editing tasks, such as global editing, local editing, text modification, and reference-guided editing. It has strong semantic understanding capabilities and can perform precise editing according to instructions. - 🌟 **Consistency Preservation**: LongCat-Image-Edit has strong consistency preservation capabilities, specifically scrutinizes whether attributes in non-edited regions, such as layout, texture, color tone, and subject identity, remain invariant unless targeted by the instruction, is well demonstrated in multi-turn editing. - 🌟 **Strong Benchmark Performance**: LongCat-Image-Edit achieves state-of-the-art (SOTA) performance in image editing tasks while significantly improving model inference efficiency, especially among open-source image editing models. > [!CAUTION] > **📝 Special Handling for Text Rendering** > > For both Text-to-Image and Image Editing tasks involving text generation, **you must enclose the target text within single or double quotation marks** (both English '...' / "..." and Chinese ‘...’ / “...” styles are supported). > > **Reasoning:** The model utilizes a specialized **character-level encoding** strategy specifically for quoted content. Failure to use explicit quotation marks prevents this mechanism from triggering, which will severely compromise the text rendering capability. >
翻訳待ち・原文を表示
入力 画像→ 出力 画像
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Image-Edit-Turbo
meituan-longcatWe introduce **LongCat-Image-Edit-Turbo**, the distilled version of LongCat-Image-Edit. It achieves high-quality image editing with only 8 NFEs (Number of Function Evaluations) , offering extremely low inference latency. > [!CAUTION] > **📝 Special Handling for Text Rendering** > > For both Text-to-Image and Image Editing tasks involving text generation, **you must enclose the target text within single or double quotation marks** (both English '...' / "..." and Chinese ‘...’ / “...” styles are supported). > > **Reasoning:** The model utilizes a specialized **character-level encoding** strategy specifically for quoted content. Failure to use explicit quotation marks prevents this mechanism from triggering, which will severely compromise the text rendering capability. >
翻訳待ち・原文を表示
入力 画像→ 出力 画像
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Next
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Video
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 動画
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗LongCat-Video-Avatar-1.5
meituan-longcat基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗該当するモデルがありません
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
COST EXPLORER
モデル選びに、費用の視点も。
月間トークン数を調整してAPI費用を比較。
1 M = 100万トークン・米ドル
同一チャネルの基本テキスト料金を比較
同一チャネルの基本テキスト料金を比較
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
MODEL HANDBOOK
モデルを理解して選ぶ
API料金はどう比較しますか？+
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
オープンウェイトは無料で商用利用できますか？+
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
ランキング1位が最適ですか？+
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。