| Model | Context/Output | Knowledge Cutoff | $Input/1M | $Output/1M |
|---|---|---|---|---|
o1-preview-2024-09-12 | 128k/32k | 2023-10 | 15 | 60 |
o1-mini-2024-09-12 | 128k/64k | 2023-10 | 3 | 12 |
gpt-4o-2024-11-20 | 128k/16k | 2023-10 | 2.5 | 10 |
gpt-4o-2024-08-06 | 128k/16k | 2023-10 | 2.5 | 10 |
gpt-4o-mini-2024-07-18 | 128k/16k | 2023-10 | 0.15 | 0.60 |
gpt-4o-2024-05-13 | 128k/4k | 2023-10 | 5 | 15 |
gpt-4-turbo-2024-04-09 | 128k/4k | 2023-12 | 10 | 30 |
gpt-3.5-turbo-0125 | 16k/4k | 2021-09 | 0.5 | 1.5 |
claude-3-5-sonnet-20241022 | 200k/8k | 2024-04 | 3 | 15 |
claude-3-5-haiku-20241022 | 200k/8k | 2024-07 | 1 | 5 |
claude-3-opus-20240229 | 200k/4k | 2023-08 | 15 | 75 |
claude-3-sonnet-20240229 | 200k/4k | 2023-08 | 3 | 15 |
claude-3-haiku-20240307 | 200k/4k | 2023-08 | 0.25 | 1.25 |
gemini-1.5-pro | 1M(2M)/8k | early 2023 | 0 (1.25/2.5*) | 0 (5-10*) |
gemini-1.5-flash | 1M/8k | early 2023 | 0 (0.075-0.15*) | 0 (0.30-0.60*) |
grok-beta | 128k | 5 | 15 | |
| * >128k tokens | ||||