curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}
'

{
  "id": "chatcmpl-a6613b56-c61c-94ba-9a9f-43d4cdc7d77a",
  "object": "chat.completion",
  "request_id": "req-7f3a2c1e8b9d4f0a",
  "created": 1777021417,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm GLM-5.3, and I can help you with a variety of tasks such as conversation, reasoning, writing, and code.",
        "reasoning_content": "Let me first analyze this problem...",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 346,
    "total_tokens": 370,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 321
    }
  },
  "web_search": [
    {
      "icon": "<string>",
      "title": "<string>",
      "link": "<string>",
      "media": "<string>",
      "publish_date": "<string>",
      "content": "<string>",
      "refer": "<string>"
    }
  ],
  "content_filter": [
    {
      "role": "assistant",
      "level": 1
    }
  ]
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/credits"
  }
}

{
  "error": {
    "code": 403,
    "message": "Access denied for this model",
    "type": "permission_error",
    "param": "model"
  }
}

{
  "error": {
    "code": 404,
    "message": "Specified model not found",
    "type": "not_found_error",
    "param": "model",
    "fallback_suggestion": "glm-5.3"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 123,
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "fallback_suggestion": "<string>"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

Chat Completions API

GLM All-Model API - Chat Completions Reference

Call GLM series models through the OpenAI Chat Completions protocol, choosing the specific model with the model parameter
Synchronous processing that returns the conversation content in real time
Text conversation: single-turn or multi-turn contextual conversation; glm-5.3-flash and glm-5.3-flashx additionally support image input
System prompt: customise the AI’s role and behaviour through a role=system message
Deep thinking: thinking.type controls the chain of thought and reasoning_effort adjusts the reasoning depth; the reasoning is returned in reasoning_content
Streaming: SSE streaming responses are supported (stream=true)
Tool calling: function calling and web search are supported (web_search, up to 128 tools)
Structured output: JSON mode is enabled through response_format

About streaming responses: when stream=true, results come back over Server-Sent Events, each message formatted as data: {JSON} and the stream ending with data: [DONE]. Each chunk (ChatCompletionChunk) carries id, created, model, choices and optionally usage and content_filter; inside it, choices[].delta returns incremental role / content / reasoning_content / tool_calls, and choices[].finish_reason gives the termination reason in the final chunk.

POST

chat

completions

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}
'

{
  "id": "chatcmpl-a6613b56-c61c-94ba-9a9f-43d4cdc7d77a",
  "object": "chat.completion",
  "request_id": "req-7f3a2c1e8b9d4f0a",
  "created": 1777021417,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm GLM-5.3, and I can help you with a variety of tasks such as conversation, reasoning, writing, and code.",
        "reasoning_content": "Let me first analyze this problem...",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 346,
    "total_tokens": 370,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 321
    }
  },
  "web_search": [
    {
      "icon": "<string>",
      "title": "<string>",
      "link": "<string>",
      "media": "<string>",
      "publish_date": "<string>",
      "content": "<string>",
      "refer": "<string>"
    }
  ],
  "content_filter": [
    {
      "role": "assistant",
      "level": 1
    }
  ]
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/credits"
  }
}

{
  "error": {
    "code": 403,
    "message": "Access denied for this model",
    "type": "permission_error",
    "param": "model"
  }
}

{
  "error": {
    "code": 404,
    "message": "Specified model not found",
    "type": "not_found_error",
    "param": "model",
    "fallback_suggestion": "glm-5.3"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 123,
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "fallback_suggestion": "<string>"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

BaseURL: The default BaseURL is https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.

Thinking switch. enabled turns thinking on and is the default for all models. disabled turns it off only on glm-5.2.glm-5.3, glm-5.3-flash and glm-5.3-flashx always think. Passing disabled retains the default thinking mode; it neither disables thinking nor sets the effort to low. To reduce effort, set reasoning_effort=low. After switching from glm-5.2 to the 5.3 series, thinking remains enabled and thinking tokens are billed as output even if thinking.type=disabled is retained.

reasoning_effort: Reasoning effort, default max. Compatibility rules for glm-5.3 / glm-5.3-flash / glm-5.3-flashx

Supplied value	Effective thinking level
`low` / `high` / `max`	Unchanged
`xhigh`	`max`
`medium`	`high`
`minimal` / `none`	`low`; thinking remains enabled

minimal and none do not disable thinking on the 5.3 series. Thinking tokens are billed as output. Unrecognized values are unchanged and have no compatibility mapping; use the listed values. These mappings do not apply to glm-5.2. glm-5.2 supports max, xhigh, high, medium, low, minimal and none. xhigh is equivalent to max; medium / low are equivalent to high; minimal / none can disable thinking. thinking.type=disabled can also turn it off. Use max for complex tasks such as coding.

User message content.

String: plain text, supported by every model
Content block array: text and images mixed, supported only by glm-5.3-flash and glm-5.3-flashx

Sending image content blocks to glm-5.3 or glm-5.2 returns an error.

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:glm-5.3

required

Model to call:

Model ID	Positioning	Thinking control	Image input
`glm-5.3`	Flagship model, with across-the-board gains on complex software engineering and agent tasks and a large step up in coding; 1M context	Always enabled; effective levels: low / high / max. See reasoning_effort for compatible values.	Not supported
`glm-5.3-flash`	Lightweight multimodal model with a hybrid sparse and linear attention architecture, extremely low cost and native vision; 1M context	Same as `glm-5.3`	Supported, see the `messages` field
`glm-5.3-flashx`	Multimodal model with image input; 1M context	Same as `glm-5.3`	Supported, see the `messages` field
`glm-5.2`	Previous-generation flagship, complex reasoning and very long context; 1M context	Can be turned off with `thinking.type: "disabled"`; `reasoning_effort` supports all 7 levels	Not supported

Available options:

glm-5.3,

glm-5.3-flash,

glm-5.3-flashx,

glm-5.2

Example:

"glm-5.3"

messages

(System Message · object | User Message · object | Assistant Message · object | Tool Message · object)[]

required

The list of conversation messages, containing the full context of the current conversation

Supports four roles: system, user, assistant, tool. Messages of different roles have different field structures; please select the corresponding role to view details. Must contain at least 1 message, and cannot consist solely of system or assistant messages.

Minimum array length: 1

System Message
User Message
Assistant Message
Tool Message

Show child attributes

stream

boolean

default:false

Whether to enable streaming output mode

false: The model generates the complete response and returns it all at once (default), suitable for short text and batch processing
true: Returns chunks in real time via Server-Sent Events (SSE), suitable for chat and long text; returns data: [DONE] when the stream ends

Example:

false

thinking

object

Controls whether to enable the chain of thought (Chain of Thought)

Show child attributes

reasoning_effort

enum<string>

default:max

Reasoning effort, default max.

Compatibility rules for glm-5.3 / glm-5.3-flash / glm-5.3-flashx

Supplied value	Effective thinking level
`low` / `high` / `max`	Unchanged
`xhigh`	`max`
`medium`	`high`
`minimal` / `none`	low; thinking remains enabled

minimal and none do not disable thinking on the 5.3 series. Thinking tokens are billed as output. Unrecognized values are unchanged and have no compatibility mapping; use the listed values. These mappings do not apply to glm-5.2.

glm-5.2 supports max, xhigh, high, medium, low, minimal and none. xhigh is equivalent to max; medium / low are equivalent to high; minimal / none can disable thinking. thinking.type=disabled can also turn it off. Use max for complex tasks such as coding.

Available options:

max,

xhigh,

high,

medium,

low,

minimal,

none

Example:

"max"

do_sample

boolean

default:true

Whether to enable the sampling strategy

true (default): Uses temperature / top_p for random sampling, producing more varied output
false: Always selects the highest-probability token (greedy decoding), producing more deterministic output; in this case temperature and top_p are ignored

For tasks requiring consistency and reproducibility (such as code generation and translation), setting this to false is recommended

Example:

true

temperature

number<float>

default:1

Sampling temperature, controlling the randomness and creativity of the output

Notes:

Value range: [0.0, 1.0], limited to two decimal places
Higher values (e.g. 0.8): more random and creative, suitable for creative writing
Lower values (e.g. 0.2): more stable and deterministic, suitable for factual Q&A and code generation
Default value: 1.0

Recommendation: Do not adjust both temperature and top_p at the same time

Required range: 0 <= x <= 1

Example:

1

top_p

number<float>

default:0.95

Nucleus Sampling parameter, an alternative to temperature sampling

Notes:

Value range: [0.01, 1.0], limited to two decimal places
The model only considers candidate tokens whose cumulative probability reaches top_p; for example, 0.1 means only the top 10% probability tokens are considered
Smaller values produce more focused and consistent output; larger values increase diversity
Default value: 0.95

Recommendation: Do not adjust both temperature and top_p at the same time

Required range: 0.01 <= x <= 1

Example:

0.95

max_tokens

integer

Upper limit on the number of output tokens

Note:

The GLM series supports up to 131,072 tokens (128K) of output; setting at least 1024 is recommended
When thinking is on, chain-of-thought tokens also count towards this limit
If generation is cut off with length, try raising this value

Required range: 1 <= x <= 131072

Example:

1024

tools

(Function Tool · object | Web Search Tool (Web Search) · object)[]

The list of tools the model may call

Note:

Function calling (function) and web search (web_search) are supported
Up to 128 functions
Of these, web_search is billed separately per call when a search actually happens; the other tools carry no extra charge

Maximum array length: 128

Function Tool
Web Search Tool (Web Search)

Show child attributes

tool_choice

enum<string>

default:auto

Controls how the model selects which function to call

Notes: Only takes effect when the tool type is function; defaults to and only supports auto (the model automatically decides whether to call a tool)

Available options:

auto

Example:

"auto"

stop

string[]

The list of stop words

Notes:

When the generated text encounters a specified string, generation stops immediately (the stop word itself is not included in the returned text)
Currently only a single stop word is supported, in the format ["stop_word1"], for example ["Human:"]

Maximum array length: 4

Example:

["Human:"]

response_format

object

Specifies the model's response output format; defaults to text

Notes:

{ "type": "json_object" } enables JSON mode, and the model returns valid JSON-formatted data, suitable for scenarios such as structured data extraction
When using JSON mode, it is recommended to explicitly request JSON output in the system or user message

Show child attributes

request_id

string

Unique request identifier

Notes:

Passed by the client, 6-64 characters long; using UUID format is recommended to ensure uniqueness
If not provided, the platform will generate one automatically

Required string length: 6 - 64

Example:

"req-7f3a2c1e8b9d4f0a"

user_id

string

Unique identifier of the end user

Notes: 6-128 characters long; using a unique identifier that does not contain sensitive information is recommended, which can help the platform monitor and detect abusive behavior

Required string length: 6 - 128

Example:

"user-abc123456"

Response

Chat completion generated successfully

string

Task ID

Example:

"chatcmpl-a6613b56-c61c-94ba-9a9f-43d4cdc7d77a"

object

enum<string>

Response type

Available options:

chat.completion

Example:

"chat.completion"

request_id

string

Request ID (returned when request_id is provided in the request)

Example:

"req-7f3a2c1e8b9d4f0a"

created

integer

Request creation time, Unix timestamp (seconds)

Example:

1777021417

model

string

Model name

Example:

"glm-5.3"

choices

object[]

The list of model responses

Show child attributes

usage

object

Token usage statistics returned when the call ends

Show child attributes

web_search

object[]

Web search-related information, returned when the web_search tool is used and a search is triggered

Show child attributes

content_filter

object[]

Content safety-related information

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

GLM All-Model API - Chat Completions Reference

Authorizations

Body

Response