AI NEWS・モデル情報能力を知り、根拠ある選択を。 ↗基本情報を先に収録・詳細を随時追加
THE AI MODEL DIRECTORY ここからモデルを探す

あなたに合う AIモデルを。

言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。

人気の検索
84,991 件のモデル13202 社の提供元・公開者45 件の機能分類465件の比較可能な料金・30件の公開評価
Tテキスト生成▧画像生成▷動画生成⌘コード生成◖音声合成♫音楽生成⬡3Dモデリング▤文書分析
DISCOVER & COMPARE

AIモデルを探す 2428

注目のモデルを見つける

- 中英日韩四个语种,以及中英日韩四个语种的跨语种能力(Multilingual and Crosslingual capability in English, Chinese, Japanese and Korean); - RAG优化,适配更多真实业务场景(RAG adaptation for more domains, including Education, Law, Finance, Medical, Literature, FAQ, Textbook, Wikipedia, etc.); - BCEmbedding 适配长文本做rerank(Handle long passages reranking more than 512 limit in BCEmbedding ); - RerankerModel可以提供 **“绝对”分数**,低质量passage过滤阈值推荐0.35或0.4。(RerankerModel provides **"meaningful" (for filtering bad passages with a threshold of 0.35 or 0.4) similarity score**) - **最佳实践(Best practice)** :embedding召回top50-100片段,reranker对这50-100片段精排,最后取top5-10片段。(1. Get top 50-100 passages with bce-embedding-base_v1 for "`recall`"; 2. Rerank passages with bce-reranker-base_v1 and get top 5-10 for "`precision`" finally. ) - `BCEmbedding`技术博客( **Technical Blog** ): 为RAG而生-BCEmbedding技术报告 - Related link for **EmbeddingModel** : bce-embedding-base_v1 - RAG applications: QAnything, ragflow, HuixiangDou, ChatPDF. - Efficient inference framework: ChatLLM.cpp, Xinference, mindnlp (Huawei GPU, 华为GPU).

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 ↗
出典・文書 ↗

FactCC

manueldeprada

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 ↗
出典・文書 ↗

The smallest decider: a language model that does not generate text. It reads a **state** (a string or any JSON value) and a set of **typed questions** and returns a probability distribution for every question from a single forward pass: Choice (2-255 options, optionally described), Score (2-10 described levels), Noul (probability of yes). No decoding, no parsing, no output outside the options you defined. Same code, same wire format (`POST /v1/systemone`, TypeSafe Jev's format), same training recipe as the 2B: one epoch of `scripts/train.sh full` from `Qwen/Qwen3.5-0.8B-Base` over the full mixture (1.47M examples, 455M tokens, 4.5 h on one GH200). All six repositories share one interface (`decider.infer.Decider`, `POST /v1/systemone` in TypeSafe's format) and one readout: the letter logits at an answer slot, softmaxed over the options. Pick by size and input. Code, data registry, training scripts, the changelog and the per-version history: https://github.com/Mapika/decider.

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 ↗
出典・文書 ↗

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 ↗
出典・文書 ↗

A language model that does not generate text. It reads a state and one or more typed questions, each with an explicit option list, and returns a probability distribution over the options for every question from one forward pass. It is called from software, not chatted with. From v12 the state may include images. **This repository holds v12 (2026-10-20).** v11 stays available under the Hub tag `v11`, with its own card; v10 under `v10`. - **Weights:** the text model at the repository root (Qwen3.5-2B-Base architecture, bf16, 3.8 GB), loaded as before by `decider.infer.Decider`, `decider.serve` and the GGUF builds. `vision/` holds the image part: the vision tower of Qwen3.5-2B-Base (unchanged, 0.6 GB) and the config of the image-text model. The image path reuses the text model's weights. - **Code:** decider-ai 1.10.0 for images; text works with 1.4.0 and later.

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 ↗
出典・文書 ↗

GGUF files of Mapika/decider-2b v12, for llama.cpp. decider-2b does not generate text. It reads a state and one or more questions, each with an explicit option list, and returns a probability for every option from one forward pass. See the decider-2b card for what the model is, how it was trained, and where it is weak. **This repository holds the v12 files (2026-10-20).** The v11 files stay available under the Hub tag `v11`. The GGUF files hold the text model only: image input needs the PyTorch weights of Mapika/decider-2b and decider-ai 1.10.0. `decider_config.json` reads yes/no (Noul) answers at temperature 0.05, as the model's own config does (see its card); `decide_gguf.py` reads every question as Choice, at the Choice temperature. The tokenizer, `decider_config.json` (temperatures) and `decide_gguf.py` (the readout on llama.cpp) are in this repository too.

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 ↗
出典・文書 ↗

A language model that does not generate text. It reads a state and one or more typed questions, each with an explicit option list, and returns a probability distribution over the options for every question from one forward pass. It is called from software, not chatted with. From v3 the state may include images. **This repository holds v3 (2026-10-20).** v2.1 stays available under the Hub tag `v2.1`, with its own card; v2 and v1 under `v2` and `v1`. - **Weights:** the text model at the repository root (Qwen3.5-4B-Base architecture, bf16, 8.4 GB), loaded as before by `decider.infer.Decider`, `decider.serve` and the GGUF builds. `vision/` holds the image part: the vision tower of Qwen3.5-4B-Base (unchanged, 0.6 GB) and the config of the image-text model. The image path reuses the text model's weights. - **Code:** decider-ai 1.10.0 for images; text works with 1.4.0 and later.

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 ↗
出典・文書 ↗

GGUF files of Mapika/decider-4b v3, for llama.cpp. decider-4b does not generate text. It reads a state and one or more questions, each with an explicit option list, and returns a probability for every option from one forward pass. See the decider-4b card for what the model is, how it was trained, and where it is weak. **This repository holds the v3 files (2026-10-20).** The v2.1 files stay available under the Hub tag `v2.1`. The GGUF files hold the text model only: image input needs the PyTorch weights of Mapika/decider-4b and decider-ai 1.10.0. `decider_config.json` reads yes/no (Noul) answers at temperature 0.05, as the model's own config does (see its card); `decide_gguf.py` reads every question as Choice, at the Choice temperature. The tokenizer, `decider_config.json` (temperatures) and `decide_gguf.py` (the readout on llama.cpp) are in this repository too.

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 ↗
出典・文書 ↗

This model is trained using a self-concatinated dataset consisting of Norwegian Review Corpus dataset (https://github.com/ltgoslo/norec) and a sentiment dataset from huggingface (https://huggingface.co/datasets/sepidmnorozy/Norwegian_sentiment). Its purpose is merely for testing.

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 ↗
出典・文書 ↗

This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the evidence types dataset. It achieved the following results on the evaluation set: - Loss: 1.8672 - Macro f1: 0.3726 - Weighted f1: 0.7030 - Accuracy: 0.7161 - Balanced accuracy: 0.3616 The data set, as well as the code that was used to fine tune this model can be found in the GitHub repository BA-Thesis-Information-Science-Persuasion-Strategies The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP

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 ↗
出典・文書 ↗

This model is a fine-tuned version of the DistilBERT model to classify toxic comments. This model is intended to use for classify toxic online classifications. However, one limitation of the model is that it performs poorly for some comments that mention a specific identity subgroup, like Muslim. The following table shows a evaluation score for different identity group. You can learn the specific meaning of this metrics here. But basically, those metrics shows how well a model performs for a specific group. The larger the number, the better. The table above shows that the model performs poorly for the muslim and jewish group. In fact, you pass the sentence "Muslims are people who follow or practice Islam, an Abrahamic monotheistic religion." Into the model, the model will classify it as toxic. Be mindful for this type of potential bias.

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 ↗
出典・文書 ↗
COST EXPLORER

モデル選びに、費用の視点も。

コスト分析

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

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

選び方とよくある質問
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。

AI NEWS・情報から選択へ

ニュースで知り、ツールで効率化、モデルで可能性を。

AIニュースを読む ↗AIツールを探す ↗