curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello, please introduce yourself in one sentence"
    }
  ]
}
'

{
  "id": "msg_0842a705-9d0b-4eaa-b12d-09a4106326c5",
  "type": "message",
  "role": "assistant",
  "model": "glm-5.3",
  "content": [
    {
      "type": "thinking",
      "thinking": "The user asked to greet them with one word, so answering \"Hi\" will do.",
      "signature": ""
    },
    {
      "type": "text",
      "text": "Hi."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 101,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

Messages API

GLM All-Model API - Messages Quickstart

Call GLM series models through the Anthropic Messages protocol, choosing the specific model with the model parameter
model, max_tokens and messages are the only parameters you need (max_tokens is mandatory in the Anthropic protocol)
1M token context window across the series, with up to 131,072 output tokens
Thinking is on by default across the series, so the response content carries a type="thinking" block, and that part counts towards output tokens
For streaming, tool calls, image input and other capabilities, see the Reference page

POST

messages

curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello, please introduce yourself in one sentence"
    }
  ]
}
'

{
  "id": "msg_0842a705-9d0b-4eaa-b12d-09a4106326c5",
  "type": "message",
  "role": "assistant",
  "model": "glm-5.3",
  "content": [
    {
      "type": "thinking",
      "thinking": "The user asked to greet them with one word, so answering \"Hi\" will do.",
      "signature": ""
    },
    {
      "type": "text",
      "text": "Hi."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 101,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

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.

The GLM series has thinking on by default — the response content array carries a type="thinking" block, and that part counts towards output tokens. So max_tokens should not be set too low; 1024 or higher is recommended, otherwise the response may be truncated before the thinking finishes and you get no answer text.

Authorizations

Authorization

string

header

required

##All interfaces require authentication using a Bearer Token##

Get an API Key:

Visit the API Key management page to obtain your API Key

Add it to the request header when using:

Authorization: Bearer YOUR_API_KEY

Note: EvoLink uses Bearer Token authentication uniformly for /v1/messages.

Body

application/json

model

enum<string>

default:glm-5.3

required

Model to call:

Model ID	Positioning
`glm-5.3`	Flagship model, with across-the-board gains on complex software engineering and agent tasks; 1M context
`glm-5.3-flash`	Lightweight multimodal model, extremely low cost, native image input; 1M context
`glm-5.2`	Previous-generation flagship, complex reasoning and very long context; 1M context

Available options:

glm-5.3,

glm-5.3-flash,

glm-5.2

Example:

"glm-5.3"

max_tokens

integer

default:1024

required

Maximum number of tokens to generate for this request; required by the Anthropic protocol.

Note: the GLM series has thinking on by default, and the thinking content also consumes output tokens, so this value should not be too small — 1024 or higher is recommended.

Required range: 1 <= x <= 131072

Example:

1024

messages

Message · object[]

required

The list of conversation messages, in chronological order. At least one message is required.

Minimum array length: 1

Show child attributes

Response

Message object

Anthropic-style message response

string

The message's unique ID (format: msg_<uuid>)

type

enum<string>

Response object type

Available options:

message

role

enum<string>

Available options:

assistant

model

string

Model actually used

Example:

"glm-5.3"

content

object[]

The list of response content blocks

Possible block types:

thinking: the reasoning process (when thinking is enabled, which is the default)
text: the final answer text
tool_use: a tool call initiated by the model

Show child attributes

stop_reason

enum<string>

Stop reason

end_turn: natural completion (also returned when stop_sequences is hit)
max_tokens: reached the max_tokens limit
tool_use: the model triggered a tool call

Available options:

end_turn,

max_tokens,

tool_use

usage

object

Token usage statistics (Anthropic specification)

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

GLM All-Model API - Messages Quickstart

Authorizations

Body

Response