機能 · 2026-05-12
ロングコンテキストに対応した AI モデル
200K トークン以上のコンテキストを扱える LLM の比較。
これは何か
- ロングコンテキスト LLM は一度のプロンプトに 200K トークン以上を受け付けられます —— 書籍一枚、複数ファイルのコードベース、長時間の書き起こしなど。
- 一部モデルは 1M・2M トークン、さらに大規模まで拡張します。
なぜ重要か
- RAG の代替または補完になります —— チャンク検索の代わりに全文を貼れる場合があります。
- 入力が長くなると実効的な想起は低下しやすく、長プロンプトは百万トークン単価で高くなりがちです。
- 200K 超で段階価格を設けるベンダーもあります —— 詳細は各モデルページの >200K レートを参照してください。
この機能に対応するモデル 397 件
全 397 件中、上位 60 件を表示。 さらに絞り込むには モデル一覧 をご利用ください。
Frequently asked questions
How many AI models support 200K+ コンテキスト?
397 canonical models in our database currently support 200K+ コンテキスト. The list is regenerated on every data refresh, so it always reflects the latest model releases from models.dev.
What is the cheapest model with 200K+ コンテキスト?
Gemini 1.5 Flash-8B from Google is currently the lowest-priced option, at $0.037 per 1M input tokens and $0.150 per 1M output tokens. The full table above is sorted price-ascending.
Which model with 200K+ コンテキスト has the largest context window?
Qwen Long (Alibaba (Qwen)) leads on context at 10M tokens. This may matter if you also need long-document understanding alongside 200K+ コンテキスト.
Which models are available on the most providers?
Production-readiness usually correlates with how many independent providers host the same weights. The top three by provider count are: Kimi K2.5 (45), MiniMax-M2.5 (40), GLM-5 (38).
How is 200K+ コンテキスト different from a regular LLM?
Long-context models accept ≥ 200K input tokens — enough for entire books, codebases or hours of transcripts in one prompt. Effective recall and per-token pricing both degrade with input length, so 'big context' is not always the right choice over RAG.
How often is this list updated?
Daily. Our data pipeline pulls models.dev once a day, regenerates the canonical model list, and rebuilds these pages so newly released models appear within 24 hours.
Explore more
Top models with this capability
- Gemini 1.5 Flash-8B$0.04 in / $0.15 out
- Qwen3 235B A22B Instruct 2507$0.10 in / $0.10 out
- Qwen3-235B-A22B-Thinking-2507$0.10 in / $0.10 out
- Qwen3 30B A3B Instruct 2507$0.10 in / $0.10 out
- Qwen3 30B A3B Thinking 2507$0.10 in / $0.10 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
Vendors in this list
最終更新:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.