Skip to main content
Reasoning capabilities are currently available for the OpenAI GPT OSS (gpt-oss-120b), Qwen3 (qwen3-32b), and Z.ai GLM (zai-glm-4.6, zai-glm-4.7) models. Each model family has slight variations in the parameters used to control reasoning.

​
Reasoning Format

Control how reasoning text appears in responses using the reasoning_format parameter.

​
Available Formats

FormatDescription
parsedReasoning returned in separate reasoning field; logprobs separated into reasoning_logprobs
rawReasoning prepended to content; GLM and Qwen use <think>...</think> tokens, GPT-OSS concatenates without separators
hiddenReasoning text and logprobs dropped completely (tokens still counted)
noneUses model’s default behavior

​
Default Behavior by Model

When reasoning_format is set to none or omitted, each model uses its default format:
ModelDefault Reasoning Format
Qwen3raw (hidden for JSON object/schema)
GLMtext_parsed
GPT-OSStext_parsed

​
parsed Format

Reasoning text is returned in a separate reasoning field without start/end tokens. When logprobs are enabled, reasoning logprobs are returned in a separate reasoning_logprobs field. 
from cerebras.cloud.sdk import Cerebras

client = Cerebras()

response = client.chat.completions.create(
    model="zai-glm-4.7",
    messages=[
        {
            "role": "user",
            "content": "Can you help me with this?"
        }
    ],
    logprobs=True,
    reasoning_format="parsed"
)

print(response)
When streaming, reasoning tokens are delivered in the reasoning field of the delta.

​
raw Format

Reasoning text is included in the content field, prepended to the response. For GLM and Qwen models, reasoning is wrapped in <think>...</think> tokens. All logprobs are returned together in the standard logprobs field.
Since GPT-OSS does not use thinking tokens, reasoning and content are concatenated without separators when using raw format.
The raw format is not compatible with json_object or json_schema response formats. Models that default to raw will automatically use hidden instead when structured output is requested.
from cerebras.cloud.sdk import Cerebras

client = Cerebras()

response = client.chat.completions.create(
    model="zai-glm-4.7",
    messages=[
        {
            "role": "user",
            "content": "Can you help me with this?"
        }
    ],
    logprobs=True,
    reasoning_format="raw"
)

print(response)

​
hidden Format

Reasoning text and reasoning logprobs are dropped completely from the response. The reasoning tokens are still generated and counted toward total completion tokens. 
from cerebras.cloud.sdk import Cerebras

client = Cerebras()

response = client.chat.completions.create(
    model="zai-glm-4.7",
    messages=[
        {
            "role": "user",
            "content": "Can you help me with this?"
        }
    ],
    logprobs=True,
    reasoning_format="hidden"
)

print(response)

​
Model-Specific Parameters

Each model family has its own parameter for controlling reasoning behavior.
There are key differences between the OpenAI client and the Cerebras SDK when using non-standard OpenAI parameters. These examples use the Cerebras SDK. For more info, see Passing Non-Standard Parameters.

​
GPT-OSS: reasoning_effort

Use reasoning_effort to control how much reasoning the model performs:
  • "low" - Minimal reasoning, faster responses
  • "medium" - Moderate reasoning (default)
  • "high" - Extensive reasoning, more thorough analysis
response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Explain quantum entanglement."}],
    reasoning_effort="medium"
)

​
GLM: disable_reasoning

Use disable_reasoning to toggle reasoning on or off. Set to true to disable reasoning, or false (default) to enable it. 
response = client.chat.completions.create(
    model="zai-glm-4.7",
    messages=[{"role": "user", "content": "Explain how photosynthesis works."}],
    disable_reasoning=False  # Set to True to disable reasoning
)

​
Reasoning Context Retention

Reasoning tokens are not automatically retained across requests. To maintain awareness of prior reasoning in multi-turn conversations, include the reasoning text in the content field of the assistant message. Use the same format the model outputs: for GLM and Qwen, include reasoning in <think>...</think> tags; for GPT-OSS, prepend reasoning text directly before the answer. 
# GPT-OSS: reasoning prepended directly before the answer
response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[
        {"role": "user", "content": "What is 25 * 4?"},
        {"role": "assistant", "content": "I need to multiply 25 by 4. 25 * 4 = 100. The answer is 100."},
        {"role": "user", "content": "Now divide that by 2."}
    ]
)