Funktion · 2026-05-12
KI-Modelle mit langem Kontextfenster
Modelle mit 200K Tokens oder mehr Kontextfenster.
Was ist das?
- Long-Context-LLMs akzeptieren 200K Tokens oder mehr in einem Prompt — ganze Bücher, mehrere Projektdateien oder lange Transkripte.
- Manche Modelle skalieren auf 1M, 2M oder mehr Tokens Kontext.
Warum wichtig
- Long Context ergänzt oder ersetzt RAG — Sie können alles einfügen statt nur Chunks zu retrieven.
- Recall kann mit Länge nachlassen; lange Prompts werden bei Preis pro 1M Tokens teuer.
- Stufenpreise über 200K gibt es bei manchen Anbietern — siehe Modell-Detailseiten.
397 Modelle mit dieser Funktion
Top 60 von 397 angezeigt. Im vollständigen Verzeichnis weiter filtern.
Frequently asked questions
How many AI models support 200K+ Kontext?
397 canonical models in our database currently support 200K+ Kontext. 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+ Kontext?
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+ Kontext 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+ Kontext.
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+ Kontext 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
Zuletzt aktualisiert:
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.