Models with a long context window
36 models we could call on 22 November 2026, largest window first.
Long context: largest window first
| Model | Input, $ per 1M | Output, $ per 1M | Context, tokens | First token | Tokens a second |
|---|---|---|---|---|---|
| google/gemini-2.5-pro | $1.25 | $10 | 2,000,000 | 2,228 ms | not measured |
| openai/gpt-6-luna | $0.1 | $0.5 | 1,050,000 | 995 ms | 179.1 |
| openai/gpt-6.1-terra | $1 | $5 | 1,050,000 | 1,134 ms | 94.8 |
| openai/gpt-6.1-sol | $2 | $10 | 1,050,000 | 1,298 ms | 183.2 |
| openai/gpt-6.2-astra | $8 | $40 | 1,050,000 | 1,292 ms | 94.5 |
| openai/gpt-6-astra | $10 | $50 | 1,050,000 | 1,408 ms | 186.7 |
| google/gemini-2.5-flash-lite | $0.1 | $0.4 | 1,048,576 | 531 ms | 90.6 |
| deepinfra/deepseek-ai/DeepSeek-V4.1-Flash | $0.2 | $0.6 | 1,048,576 | 489 ms | 202.3 |
| deepseek/deepseek-v4.1-flash | $0.25 | $0.75 | 1,048,576 | 426 ms | 189.3 |
| google/gemini-3.1-flash-lite-preview | $0.25 | $1.5 | 1,048,576 | 793 ms | 758.8 |
| google/gemini-3.5-flash-lite | $0.3 | $2.5 | 1,048,576 | 850 ms | 715.2 |
| google/gemini-3.6-flash | $0.75 | $3.75 | 1,048,576 | 1,713 ms | not measured |
| google/gemini-3.8-flash | $0.825 | $4.125 | 1,048,576 | 2,820 ms | not measured |
| google/gemini-3.1-pro-preview | $2 | $12 | 1,048,576 | 4,342 ms | not measured |
| anthropic/claude-haiku-5-5 | $0.1 | $0.5 | 1,000,000 | 1,013 ms | 749.2 |
| openai/gpt-5.6-luna | $0.2 | $1.2 | 1,000,000 | 797 ms | 220 |
| google/gemini-3.1-flash-lite | $0.25 | $1.5 | 1,000,000 | 858 ms | 739.6 |
| google/gemini-2.5-flash | $0.3 | $2.5 | 1,000,000 | 1,191 ms | not measured |
| openai/gpt-4.1-mini | $0.4 | $1.6 | 1,000,000 | 857 ms | 132.1 |
| google/gemini-3-flash-preview | $0.5 | $3 | 1,000,000 | 1,377 ms | not measured |
| google/gemini-3.5-flash | $1.5 | $9 | 1,000,000 | 2,069 ms | not measured |
| anthropic/claude-sonnet-5.5 | $2 | $10 | 1,000,000 | 1,545 ms | 186.6 |
| openai/gpt-4.1 | $2 | $8 | 1,000,000 | 551 ms | 296.5 |
| openai/gpt-5.6-terra | $2 | $12 | 1,000,000 | 845 ms | 222.1 |
| anthropic/claude-opus-5.5 | $4 | $20 | 1,000,000 | 1,003 ms | 252 |
| openai/gpt-5.6-sol | $4 | $20 | 1,000,000 | 1,047 ms | 245.3 |
| anthropic/claude-fable-5.1 | $10 | $50 | 1,000,000 | 2,458 ms | 571.4 |
| openai/gpt-5-nano | $0.05 | $0.4 | 400,000 | 2,712 ms | 235.4 |
| openai/gpt-5.4-nano | $0.2 | $1.25 | 400,000 | 451 ms | 159.3 |
| openai/gpt-5-mini | $0.25 | $2 | 400,000 | 4,164 ms | 124.6 |
| openai/gpt-5.4-mini | $0.75 | $4.5 | 400,000 | 575 ms | 269.3 |
| openai/gpt-5 | $1.25 | $10 | 400,000 | 4,725 ms | 167.3 |
| openai/gpt-5-search-api | $1.25 | $10 | 400,000 | 1,232 ms | 234.5 |
| openai/gpt-5.2 | $1.75 | $14 | 400,000 | 597 ms | 120.6 |
| openai/gpt-5.4 | $2.5 | $15 | 400,000 | 757 ms | 175.6 |
| openai/gpt-5.5 | $5 | $30 | 400,000 | 1,328 ms | 122.5 |
How a model gets on this list
- A model is listed here when its context window is 400,000 tokens or more and it answered our probe.
- The window is the size the price feed states; the probe does not fill it.
Other lists
- Tool calling55 models
- Vision33 models
How this page is made
Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.
Data checked · Last changed