> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek

> DeepSeek's text & code models on Kyma — DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek V3 and 1 more.

4 DeepSeek text & code models on Kyma.

| Model ID                                         | Best for                                    | Per 1M                 |
| ------------------------------------------------ | ------------------------------------------- | ---------------------- |
| [`deepseek-v4-pro`](/models/deepseek-v4-pro)     | Top reasoning, complex coding, long context | \$0.69 in · \$1.38 out |
| [`deepseek-v4-flash`](/models/deepseek-v4-flash) | General, coding, long context, value        | \$0.19 in · \$0.37 out |
| [`deepseek-v3`](/models/deepseek-v3)             | Reasoning, coding, general                  | \$0.35 in · \$0.51 out |
| [`deepseek-r1`](/models/deepseek-r1)             | Math, logic, complex reasoning              | \$0.73 in · \$2.96 out |

## Which one

Default to `deepseek-v4-flash` for new work — it gives you 1M context, native
reasoning, and the same family behaviour at a fraction of the cost. Move up to
`deepseek-v4-pro` when quality matters more than price. Stay on `deepseek-v3`
if you have a production workload already tuned to it.

`deepseek-r1` is the reasoning specialist: slower, and worth it for maths and
step-by-step analysis where you want the chain of thought exposed.