Control GLM-5.3-Flash Reasoning

GLM-5.3-Flash is an always-on reasoning model. You can control its reasoning with the following parameters:

Parameter	Data Type	Default
`parse_reasoning`	boolean	`true`
`include_reasoning`	boolean	`true`
`reasoning_effort`	enum (`low`, `high`, `max`)	`max`
`reasoning_budget`	integer	`null`
`clear_thinking`	boolean	`false`

If you don’t set a parameter, the model uses its default. You can edit a parameter to control how the model reasons.

Control Reasoning

To learn how to control the model’s reasoning, see the following sections:

Parse Reasoning

By default, reasoning’s parsed. To turn parsing off, use the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.3-Flash",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "parse_reasoning": False,
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "parse_reasoning": false,
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "parse_reasoning": false
}'

To learn more, see parse_reasoning.

Include Reasoning

By default, reasoning’s included. To exclude it, use the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.3-Flash",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "include_reasoning": False,
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "include_reasoning": false,
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "include_reasoning": false
}'

To learn more, see include_reasoning.

Set the Reasoning Effort

By default, reasoning effort’s set to max. To set it to low, use the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.3-Flash",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "reasoning_effort": "low",
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "reasoning_effort": "low",
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "reasoning_effort": "low"
}'

To learn more, see reasoning_effort.

Set a Reasoning Budget

By default, there’s no reasoning budget. To set one (for example, to 10,000 tokens), use the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.3-Flash",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "reasoning_budget": 10000,
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "reasoning_budget": 10000,
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "reasoning_budget": 10000
}'

To learn more, see reasoning_budget.

Clear Reasoning

By default, reasoning’s preserved. To clear it, use the following code:

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.friendli.ai/serverless/v1",
  api_key=os.environ["FRIENDLIAI_API_KEY"],
)

completion = client.chat.completions.create(
  model="zai-org/GLM-5.3-Flash",
  messages=[
    {"role": "system", "content": "You are a friendly assistant."},
    {"role": "user", "content": "Describe FriendliAI in one sentence."},
  ],
  extra_body={
    "chat_template_kwargs": {
      "clear_thinking": True,
    },
  },
)

print(completion.choices[0].message)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.friendli.ai/serverless/v1",
  apiKey: process.env.FRIENDLIAI_API_KEY,
})

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a friendly assistant." },
    { role: "user", content: "Describe FriendliAI in one sentence." },
  ],
  "chat_template_kwargs": {
    "clear_thinking": true,
  },
})

console.log(completion.choices[0].message)

curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $FRIENDLIAI_API_KEY" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a friendly assistant."},
      {"role": "user", "content": "Describe FriendliAI in one sentence."}
    ],
    "chat_template_kwargs": {
      "clear_thinking": true
    }
}'

To learn more, see clear_thinking.

Models

Agents

SDKs

Tutorials

Control GLM-5.3-Flash Reasoning

Control Reasoning

​Control Reasoning

Control Reasoning