AI NEWS.ccAIが動く、未来が変わる
♡ 保存済み 0
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 84991

注目のモデルを見つける

**Abliterated Gemma 4 31B Dense — 60 layers, hybrid sliding/global attention, multimodal VL** > **Recommended: Run in vMLX** for best experience including thinking mode support, repetition penalty, and vision capabilities. - **Improved abliteration**: Higher quality refusal vector extraction - **Thinking-ON stability**: Clean thinking cycle — no more degenerate loops - **Same compliance**: 93.7% HarmBench - **Architecture-aware**: Tuned for Gemma 4's hybrid attention design

翻訳待ち・原文を表示

画像質問応答
入力 テキスト · 画像→ 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 **CRACK** release by dealignai · Twitter @dealignai > [!IMPORTANT] > **Runtime notes** — field-tested on 8× DGX Spark GB10 by @0xMagnus (discussion): > > - **`reasoning_effort` only honors `"low"` and `"high"`.** Every other value — `off`, `medium`, `max`, unset, or an unquoted YAML `off:` (parses as boolean `false`) — falls through to `max`. There is no way to disable reasoning on this checkpoint; pass `"low"` for minimum. > - **On FP8, prefer `low` for agent / tool-loop use.** At `high`/`max` the model can spend the whole `max_tokens` budget inside ` ` and return zero answer tokens (finish=`length`); sampling params (temp 0 + rep 1.05, temp 0.7 / top-p 0.95) do not rescue it. It is budget exhaustion, not a loop. If you must run `high`/`max`, give `max_tokens ≥ 8000`. > - **Reasoning text is in `message.reasoning`**, not `message.reasoning_content`. > - **MTP:** non-functional on stock vLLM, but reported working on ciprianveg's B12X sparse-MLA vLLM fork with `--draft-attention-backend B12X_MLA_SPARSE` (+48% decode on coding prompts). > - **1M context via decode-context-parallel is closed** on `glm_moe_dsa` in vLLM today (DSA indexer `k_cache` is replicated across DCP ranks while MLA KV is sharded → `page size is not divisible by target page size and cannot be padded` for `fp8_ds_mla`). Practical TP8 H200 ceiling: ~131K w/MTP, ~160K w/o. Pipeline-parallel (PP2 × TP4) profiles fine, but the MTP draft does not implement `SupportsPP`. **This is a CYBERSECURITY-DOMAIN CRACK of GLM-5.3-FP8 — not a general-purpose uncensor.**

翻訳待ち・原文を表示

テキスト生成
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 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build

翻訳待ち・原文を表示

テキスト生成
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 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build. Set > `fps`, which every build honours. > - **Pixel controls: use `mm_processor_kwargs.max_image_tokens` / `min_image_tokens`.** > `max_pixels`, `min_pixels`, `size` and `detail` return HTTP 200 and

翻訳待ち・原文を表示

分類準備中
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 ↗
出典・文書 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build

翻訳待ち・原文を表示

分類準備中
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 ↗
出典・文書 ↗

Refusal-direction–ablated GGUF of `openbmb/MiniCPM-V-4.7-35B-A3B`, the 35B-A3B Qwen3.5-moe-text (hybrid GatedDeltaNet + Full-Attention + 256 routed experts + 1 shared expert) multimodal model. Surgery removes the model's refusal direction from **all three residual-stream writer tiers** of the Qwen3.5 hybrid architecture — the SSM output path is the critical tier that single-tier surgeries miss on this architecture. Multimodal (16× + 4× projectors) and DSpark speculative-decoding paths are preserved. HarmBench-240 (standard + contextual + copyright splits), MMLU-200 (balanced subjects, logit-eval), multi-turn 5-scenario coherence, harsh-10 hot categories. Multimodal verified on synthetic image (number `7342` + red square + blue circle).

翻訳待ち・原文を表示

画像質問応答
入力 テキスト · 画像→ 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 ↗

**Standard dense Llama-family 33B · 52 layers · 7168 hidden · GQA 56Q/8KV · think on/off · 512K context** > **UNCENSORED** = refusal-removed GGUF build of **Nanbeige/Nanbeige4.3-33B**. Three quants in one place: **Q6_K (25.3 GB)**, **Q4_K_M (18.7 GB)**, **IQ2_XXS (8.7 GB)**. All ship with a fresh matching importance matrix (imatrix) over 1M tokens of mixed code / reasoning / agentic / terminal / conversation calibration content, with exact source-tokenizer parity against the pinned llama.cpp runtime. Native thinking mode (on/off) preserved from the original chat template. > Research artifact for alignment work. This model answers requests the base refuses, including harmful ones. **Do not deploy to end users without separate downstream safety controls.**

翻訳待ち・原文を表示

テキスト生成
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 ↗