Capability · 2026-06-29
AI Models with Long Context Windows
AI models supporting 200K+ token context windows.
What is this?
- Long-context LLMs accept input of 200K tokens or more — enough for entire books, multi-file codebases or hours of transcripts in a single prompt.
- Some models scale to 1M, 2M or even 10M tokens of context.
Why it matters
- Long context is an alternative (or supplement) to RAG — instead of retrieving chunks, you can paste everything in.
- Beware that effective recall degrades with input length, and per-million-token pricing can make long prompts expensive.
- Some vendors apply tiered pricing above 200K tokens — see each model's detail page for over-200K rates.
509 models with this capability
Showing top 60 of 509. Use the full directory to filter further.
Frequently asked questions
How many AI models support 200K+ context windows?
509 canonical models in our database currently support 200K+ context windows. The list is regenerated on every data refresh, so it always reflects the latest releases tracked in our catalogue.
What is the cheapest model with 200K+ context windows?
Ling-2.6-flash from openrouter is currently the lowest-priced option, at $0.010 per 1M input tokens and $0.030 per 1M output tokens. The full table above is sorted price-ascending.
Which model with 200K+ context windows 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+ context windows.
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 K2.6 (49), Kimi K2.5 (48), GLM-5.1 (47).
How is 200K+ context windows 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 syncs 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
- Ling-2.6-flash$0.01 in / $0.03 out
- Google Gemma 3 27B Instruct$0.03 in / $0.11 out
- Qwen3 235B A22B 2507$0.07 in / $0.10 out
- Qwen3.5 9B$0.04 in / $0.15 out
- Qwen3 235B A22B Instruct 2507$0.10 in / $0.10 out
Other capabilities
Best-of lists you might also want
Pricing comparisons
Vendors in this list
Last updated:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.