Berges Reasoning
Structured, step-by-step thinking on demand. Pick the Reasoning pipeline from the sidebar when you want the model to slow down and show its work.
Reasoning is one of four pipelines Berges AI ships with. Pick it from the sidebar and the deep-thinking layer switches into a mode tuned for structured, multi-step thought: lay out the inputs, work through them in order, land on a conclusion.
It's the right choice when the answer matters more than the prose, and when getting to the answer requires staying organized through more than one or two hops.
What changes when you pick it
Lower randomness
Reasoning uses a low sampling temperature, which keeps the model consistent across runs. Ask the same question twice and you should get a similar shape of answer, which is what you want for analysis.
A reasoning-first system prompt
On top of whatever model is running, Reasoning layers a system prompt that asks for steps, evidence, and a conclusion. The Berges-style framework is the proprietary part.
Runs on every turn
While Reasoning is selected it shapes every reply, whichever model you have picked. Pick another pipeline from the sidebar when you want a different approach.
When Reasoning is the right pick
- → Math and quantitative problems
- → Multi-step decisions (e.g. "should I refinance given these numbers")
- → Debugging or root-cause analysis
- → Comparing options against explicit criteria
- → Anything where you'd want to see the work, not just the answer
Example prompts
Things people ask about Reasoning
When should I not use Reasoning?
When the question is easy or open-ended. Reasoning makes the model slower and more methodical, which is the wrong shape for "give me five name ideas" or "what time is it in Tokyo".
Is Reasoning the same as picking a bigger model?
No. Picking GLM, Qwen or Kimi from the sidebar changes which model answers. Reasoning changes how any model answers: structured steps, evidence, a conclusion, with lower randomness. You can combine the two.
Does Reasoning work with all models?
Yes. Pipelines operate on top of whichever model you pick, so the Reasoning system prompt and lower temperature apply whether the underlying model is DeepSeek, GLM, Qwen or Kimi.