Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
DeepSeek’s text & code models on Kyma — DeepSeek V4.1 Flash, DeepSeek V4 Flash Vision, DeepSeek V4 Flash and 2 more.
| Model ID | Best for | Per 1M |
|---|---|---|
deepseek-v4.1-flash | General, coding, long context, vision at value pricing | $0.27 in · $0.81 out |
deepseek-v4-flash-vision-exp | Cheap multimodal reasoning on the V4 Flash line | $0.297 in · $0.891 out |
deepseek-v4-flash | General, coding, long context, value | $0.1389 in · $0.2778 out |
deepseek-v3 | Reasoning, coding, general | $0.351 in · $0.513 out |
deepseek-r1 | Math, logic, complex reasoning | $0.7425 in · $2.957 out |
deepseek-v4-flash for new work — it gives you 1M context, native
reasoning, and the same family behaviour at a fraction of the cost. 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.