implementation detail · filed under inference & serving
Reasoning parser
A serving-time parser is selected to interpret reasoning output; the evidence names parser identifiers but does not specify their mechanisms.
Also called reasoning parser step3p5.
- sources
- 3
- models
- 2
- labs adopt it
- 2
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 3
Documented in
Evidence
3 spans quoted from the sources, strongest treatment first.
--reasoning-parser hy_v3
usedsoftware implementationin Hy3Tencent
--reasoning-parser step3p5
usedsoftware implementationin Step 3.7 FlashStepFun
--reasoning-parser step3p5
usedsoftware implementationin Step 3.7 FlashStepFun
Filed alongside
Other methods under inference & serving :: reasoning control.
Configurable reasoning effortChain-of-thought reasoningDefault thinking modeDeployment-time scalar effort controlDisabling reasoning via chat-template configurationInference-time reasoning budget controlInterleaved thinking between tool callsThinking mode selectionCross-turn persistent reasoning historyMaximum thinking effortAlways-on thinking modeclear_thinking chat-template parameterControl-token-enabled thinking modeEffort-dependent exponential token-penalty scheduleGenerate-verify-refine loopMedium-effort reasoning modeParallel-fewest-step samplingQwen3 soft thinking switchTask- and mode-specific sampling parameter recommendationsTest-time compute scalingAdaptive reasoningCapped linear reasoning-token length deductionConfigurable thinking or reasoning modeControllable thinking effort via system message and per-token cost