Configurable reasoning effort

the model thus exposes a single, reliable knob that moves the cost–accuracy operating point in a controlled and predictable way

Thinking effort is configured with the top-level `reasoning_effort` request field, which supports "low", "high", and "max" (default "max").

reasoning_effort: "no_think" (default, direct response), "low", "high" (deep chain-of-thought)

GLM-5 supports controlling the thinking budget through the reasoning_effort parameter, which accepts two levels: max and high. max is the default

GLM-5.3 offers three reasoning effort levels driven by the reasoning_effort field

GLM-5.3 always operates with reasoning enabled and supports three reasoning effort levels: low, high, and max.

GLM-5.3 supports controlling the thinking budget through the reasoning_effort parameter, which accepts three levels: low, high, and max. It defaults to max if not passed (or if set to any other value).

GLM-5.3-Flash offers three reasoning effort levels driven by the reasoning_effort field; the default is max

Native reasoning support: You can run requests with thinking off or with max thinking. Max thinking is enabled by default

Thinking effort is configured with the top-level reasoning_effort request field, which supports "low", "high", and "max" (default "max").

lets users dial 'thinking effort' up or down when they want to trade for speed

So it looks like there are just two reasoning effort levels: "high" (the default) and "no_think" (reason by disabled).

We train the models to support three reasoning levels: low, medium, and high.

Ultra is also equipped with reasoning effort control, which supports inference-time adjustment of the accuracy–compute trade-off

the reasoning effort control was also expanded to three explicit levels (low, high, max)

DeepSeek-V4.1-Flash exposes a reasoning-effort setting that allows users to trade inference cost for accuracy in a controllable manner.

The reasoning_effort parameter now supports three levels — low, high, and max — which control how much deliberation the model spends before answering.

Both V4-Pro and V4-Flash support three modes: Non-think, Think High, and Think Max

GLM-5.2 introduces two selectable effort levels: Max mode and High mode

The model supports a continuously controllable reasoning effort setting (integer 1–100) that trades inference cost for accuracy.

Ultra is also equipped with reasoning effort control, which supports inference-time adjustment of the accuracy–compute trade-off

Three selectable reasoning depths — low, medium, and high — let developers trade latency for reasoning depth

By default, the model will do medium level reasoning. To control the reasoning you can specify in the system message the reasoning level as low, medium, or high.

Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.

GLM-5.3-Flash supports controlling the thinking budget through the reasoning_effort parameter

The model supports three reasoning efforts: low, medium and high.

Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.

reasoning_effort="no_think"

M3 supports three reasoning modes through the thinking parameter

multiple thinking effort levels to balance performance and latency

The reasoning_effort parameter now supports three levels — low, high, and max — which control how much deliberation the model spends before answering.

offers three selectable reasoning levels (low, medium, and high) so developers can easily balance speed, cost, and cognitive depth

The thinking modes of V4-Pro and V4-Flash now support three thinking effort levels: low / high / max.

There are a range of approaches to this today including model ‘effort’ parameters, token limits at the request or task level, or turn limits.