COMPUTED FROM THE CATALOG
Best models for long documents, by context window
Models that can read a million tokens or more at once, largest context window first.
How this list is computed
Text-writing models with a context window of at least 1,000,000 tokens and a listed price. Sorted by context window, largest first; ties go to the lower input price, then the name.
119 of the 350 models in the 2026-10-24 snapshot qualify. This is not a quality ranking: SEKAI has no benchmark data.
| # | Model | Provider | Added | Context | Input | Output |
|---|---|---|---|---|---|---|
| 1 | Grok 4.202M-token context window | SpaceXAI | 2026-03-31 | 2M | $1.25 | $2.50 |
| 2 | Grok 4.20 Multi-Agent2M-token context window | SpaceXAI | 2026-03-31 | 2M | $1.25 | $2.50 |
| 3 | Llama 4 Scout1.31M-token context window | Meta | 2025-04-05 | 1.31M | $0.100 | $0.300 |
| 4 | GPT-6 Luna1.05M-token context window | OpenAI | 2026-09-22 | 1.05M | $0.100 | $0.500 |
| 5 | GPT-6 Luna Pro1.05M-token context window | OpenAI | 2026-09-22 | 1.05M | $0.100 | $0.500 |
| 6 | MiMo-V2.51.05M-token context window | Xiaomi | 2026-04-22 | 1.05M | $0.120 | $0.240 |
| 7 | MiMo-V2.6-Flash1.05M-token context window | Xiaomi | 2026-09-21 | 1.05M | $0.140 | $0.280 |
| 8 | GPT-5.6 Luna1.05M-token context window | OpenAI | 2026-07-09 | 1.05M | $0.200 | $1.20 |
| 9 | GPT-5.6 Luna Pro1.05M-token context window | OpenAI | 2026-07-09 | 1.05M | $0.200 | $1.20 |
| 10 | MiMo-V2.5-Pro1.05M-token context window | Xiaomi | 2026-04-22 | 1.05M | $0.300 | $0.610 |
Questions and answers
Which model comes first in this list?
Grok 4.20 from SpaceXAI: 2M-token context window.
How many models meet the criteria?
119 of the 350 models in the 2026-10-24 snapshot.
Which qualifying model has the lowest input price?
Lyria 3 Clip Preview (Google), which OpenRouter lists as free.
Answers are computed from the 2026-10-24 catalog snapshot.