> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# GLM-5.2 - Anthropic Compatible API
> - Call the GLM-5.2 model via the Anthropic Messages protocol
- Request / response structures aligned with the Anthropic API
- **System prompt**: Passed via the top-level `system` field
- **Thinking mode**: GLM-5.2 has thinking enabled by default; thinking content is returned via `content[type=thinking]` blocks; pass `thinking.type=disabled` to turn it off
- **Streaming output**: SSE event stream
- **Tool calling**: Compatible with the Anthropic `tool_use` / `tool_result` flow
- ⚠️ **No multimodal support**: GLM-5.2 is a text-only model, and image / video content blocks are ignored
**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.
## OpenAPI
````yaml en/api-manual/language-series/glm-5.2/glm-5.2-messages.json POST /v1/messages
openapi: 3.1.0
info:
title: GLM-5.2 Anthropic-Compatible API
description: >-
Complete API reference for calling GLM-5.2 via the Anthropic Messages
protocol.
**Compatibility notes**:
- Path: `/v1/messages` (Anthropic standard path)
- Request / response structures match the Anthropic Messages API
- Supported fields: `model` `messages` (required) `system` `max_tokens`
`temperature` `top_p` `top_k` `stop_sequences` `stream` `thinking` `tools`
`tool_choice` `metadata`
**Model capabilities**:
- Thinking mode: GLM-5.2 is a reasoning model and **has thinking enabled by
default**; thinking content is returned via `content[type=thinking]` blocks
and counts toward output tokens. When not needed, explicitly pass
`thinking.type=disabled` to turn it off and save tokens
- **Text-only model**: ⚠️ Does not support multimodal inputs such as images
/ video (image content blocks passed in are ignored)
- Prompt caching: Implicit caching is supported, and requests with the same
prefix automatically hit the cache (reflected in `cache_read_input_tokens`,
with no need to set `cache_control` manually); the cache needs to warm up,
and hits become more stable after the same prefix is requested several
times; `cache_creation_input_tokens` is always 0
license:
name: MIT
version: 1.0.0
servers:
- url: https://direct.evolink.ai
description: Production (Recommended, better support for text models)
- url: https://api.evolink.ai
description: Alternative URL
security:
- bearerAuth: []
tags:
- name: Messages
description: Anthropic Messages protocol interface
paths:
/v1/messages:
post:
tags:
- Messages
summary: GLM-5.2 Messages Interface (Anthropic-Compatible)
description: >-
- Call the GLM-5.2 model via the Anthropic Messages protocol
- Request / response structures aligned with the Anthropic API
- **System prompt**: Passed via the top-level `system` field
- **Thinking mode**: GLM-5.2 has thinking enabled by default; thinking
content is returned via `content[type=thinking]` blocks; pass
`thinking.type=disabled` to turn it off
- **Streaming output**: SSE event stream
- **Tool calling**: Compatible with the Anthropic `tool_use` /
`tool_result` flow
- ⚠️ **No multimodal support**: GLM-5.2 is a text-only model, and image
/ video content blocks are ignored
operationId: createMessageGLM52
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateMessageRequest'
examples:
simple:
summary: Minimal runnable request
value:
model: glm-5.2
max_tokens: 1024
messages:
- role: user
content: Hello, world
system_prompt:
summary: With a system prompt
value:
model: glm-5.2
max_tokens: 2048
system: You are a seasoned technical editor.
messages:
- role: user
content: Introduce GLM-5.2 in three sentences.
disable_thinking:
summary: Disable thinking mode (save tokens)
value:
model: glm-5.2
max_tokens: 512
thinking:
type: disabled
messages:
- role: user
content: 'In one sentence: what is the capital of Japan?'
stop_sequences:
summary: Custom stop sequences
value:
model: glm-5.2
max_tokens: 50
thinking:
type: disabled
stop_sequences:
- '3'
messages:
- role: user
content: 'Output exactly: 1 2 3 4 5 6'
tool_use:
summary: Tool calling (Anthropic tool_use style)
value:
model: glm-5.2
max_tokens: 2048
messages:
- role: user
content: Check the weather in Tokyo and tell me
tools:
- name: get_weather
description: Query the current weather of a specified city
input_schema:
type: object
properties:
city:
type: string
description: 'City name, for example: Tokyo'
required:
- city
tool_choice:
type: auto
streaming:
summary: Streaming output (SSE)
value:
model: glm-5.2
max_tokens: 1024
stream: true
messages:
- role: user
content: Write a short poem about spring
responses:
'200':
description: Message object
content:
application/json:
schema:
$ref: '#/components/schemas/MessageResponse'
examples:
with_thinking:
summary: Includes a thinking content block by default
value:
id: msg_0842a705-9d0b-4eaa-b12d-09a4106326c5
type: message
role: assistant
model: glm-5.2
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
tool_use:
summary: Triggers a tool call (stop_reason=tool_use)
value:
id: msg_067e85db-53df-43a1-bd38-09c53375f2f0
type: message
role: assistant
model: glm-5.2
content:
- type: tool_use
id: toolu_36b8a98e284c426799f08612
name: get_weather
input:
city: Tokyo
stop_reason: tool_use
usage:
input_tokens: 161
output_tokens: 11
cache_creation_input_tokens: 0
cache_read_input_tokens: 0
prompt_tokens_details:
cached_tokens: 0
'400':
description: Invalid request parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
request_id: req_xxx
error:
type: invalid_request_error
message: Invalid request
'401':
description: Authentication error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
error:
type: authentication_error
message: Authentication error
'402':
description: Insufficient quota
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
error:
type: billing_error
message: Insufficient quota
'403':
description: Permission error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
error:
type: permission_error
message: Permission denied
'404':
description: Model or resource not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
error:
type: not_found_error
message: Model not found
'429':
description: Rate limited
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
type: error
error:
type: rate_limit_error
message: Rate limited
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'502':
description: Gateway error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
components:
schemas:
CreateMessageRequest:
type: object
required:
- model
- messages
properties:
model:
type: string
description: The model to call
enum:
- glm-5.2
example: glm-5.2
max_tokens:
type: integer
description: >-
The upper limit on the length of generated content (number of
tokens)
**Notes**:
- Tokens produced by thinking also count toward this limit
- When the limit is reached, content is truncated and the response
returns `stop_reason=max_tokens`
minimum: 1
example: 1024
messages:
type: array
description: >-
The list of conversation messages, alternating between user /
assistant by turn
**Notes**:
- Must contain at least 1 message
- The last message is usually `role=user`
- Multi-turn context is supported, and the model references prior
messages
items:
$ref: '#/components/schemas/InputMessage'
minItems: 1
system:
description: >-
System prompt, used to set the AI's role and behavior
**Notes**:
- Supports a string or an array of content blocks
- Passed via the top-level `system` field (do not place it inside
messages)
- The model follows the system constraints
- ⚠️ **An overly long system may be truncated**: For long context,
place it in `messages` rather than piling everything into `system`
oneOf:
- type: string
example: You are a helpful assistant.
- type: array
description: >-
System prompt in content-block array format. text blocks may
carry cache_control
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
cache_control:
$ref: '#/components/schemas/CacheControl'
temperature:
type: number
description: >-
Sampling temperature
**Notes**:
- Higher values make output more varied, lower values more
deterministic
- Recommended range `[0, 1]`
minimum: 0
maximum: 1
example: 1
top_p:
type: number
description: >-
Nucleus sampling threshold
**Notes**:
- Range `[0, 1]`
- It is recommended not to adjust temperature and top_p at the same
time
minimum: 0
maximum: 1
example: 0.9
top_k:
type: integer
description: >-
Sample only from the K highest-probability tokens (an
Anthropic-specific parameter)
**Notes**:
- Smaller values make output more deterministic, larger values make
candidates more diverse
minimum: 0
example: 10
stop_sequences:
type: array
description: >-
Custom stop sequences: generation stops when it hits any of these
strings
**Notes**:
- Hitting one truncates output, and content before the hit is
returned normally
- ⚠️ **Note**: When a stop sequence is hit, GLM-5.2 returns
`stop_reason` as `end_turn` (rather than the Anthropic-standard
`stop_sequence`), and the response does not include a
`stop_sequence` field. If your client relies on
`stop_reason=="stop_sequence"` to detect a hit, special handling is
required
items:
type: string
example:
- |+
stream:
type: boolean
description: >-
Whether to return via SSE streaming
- `true`: Server-Sent Events streaming (standard Anthropic event
sequence: message_start / content_block_start / content_block_delta
/ message_delta / message_stop)
- `false`: Returns the complete response all at once (default)
default: false
example: false
thinking:
type: object
description: >-
Controls deep thinking
**Notes**:
- GLM-5.2 is a reasoning model, and **thinking is enabled by default
when this field is not passed**
- When enabled, the response `content` array includes a
`type="thinking"` reasoning-process block (billed as output tokens,
and `signature` may be an empty string)
- Pass `{"type":"disabled"}` to turn off thinking, significantly
reducing output tokens
- ⚠️ **Only the binary `type` toggle takes effect**: thinking budget
/ level parameters such as `budget_tokens` and `effort` have no
effect (they are ignored), so the amount of thinking cannot be
finely controlled
required:
- type
properties:
type:
type: string
enum:
- enabled
- disabled
description: |-
- Not passing the thinking field: thinking is enabled by default
- `disabled`: turn off thinking and answer directly
- `enabled`: the Anthropic-standard explicit enable value
tools:
type: array
description: >-
The list of tool definitions
**Notes**:
- Follows the Anthropic tool definition spec
- `input_schema` uses a JSON Schema object
- The model returns standard `tool_use` blocks with
`stop_reason=tool_use`
items:
$ref: '#/components/schemas/Tool'
tool_choice:
type: object
description: Tool selection strategy
required:
- type
properties:
type:
type: string
enum:
- auto
- none
description: |-
- `auto`: the model decides on its own whether to call a tool
- `none`: tool calls are disallowed
metadata:
type: object
description: Request metadata
properties:
user_id:
type: string
description: >-
A unique identifier representing the end user, which can be used
for per-user monitoring and abuse detection (using a hashed ID
is recommended)
MessageResponse:
type: object
description: Anthropic-style message response
properties:
id:
type: string
description: 'The message''s unique ID (format: `msg_`)'
type:
type: string
enum:
- message
description: Response object type
role:
type: string
enum:
- assistant
model:
type: string
description: The model actually used
example: glm-5.2
content:
type: array
description: >-
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
items:
$ref: '#/components/schemas/OutputContentBlock'
stop_reason:
type: string
description: >-
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
enum:
- end_turn
- max_tokens
- tool_use
usage:
$ref: '#/components/schemas/AnthropicUsage'
ErrorResponse:
type: object
properties:
type:
type: string
enum:
- error
error:
type: object
properties:
type:
type: string
description: >-
Error type (e.g. invalid_request_error / authentication_error /
billing_error, etc.)
message:
type: string
description: Error description
request_id:
type: string
description: Request tracing ID
InputMessage:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- user
- assistant
description: >-
The role of the message sender, alternating between user / assistant
- `user`: user message (also used to pass back `tool_result` blocks)
- `assistant`: the assistant's historical replies (may contain
`text` / `thinking` / `tool_use` blocks)
⚠️ **`system` is not accepted**: pass system prompts via the
top-level `system` field.
content:
description: >-
Message content
**Notes**:
- For plain text, pass a string directly
- For structured content, pass an array of content blocks (`text` /
`tool_use` / `tool_result` / `thinking`)
- ⚠️ GLM-5.2 is a text-only model, and `image` / `video` content
blocks are ignored
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ContentBlock'
CacheControl:
type: object
description: >-
Prompt caching marker
**Notes**: GLM-5.2 uses implicit caching (built automatically per
identical prefix, with hits shown in `cache_read_input_tokens`, and
requires warm-up) and does not rely on this explicit marker;
`cache_control` can be passed normally but may be ignored, and it does
not affect implicit caching.
required:
- type
properties:
type:
type: string
enum:
- ephemeral
description: Cache marker type
Tool:
type: object
required:
- name
- input_schema
properties:
name:
type: string
description: |-
Tool name
**Notes**:
- Only `a-zA-Z0-9_-` are allowed
- Maximum 64 characters
description:
type: string
description: >-
A description of the tool's capability, for the model to decide when
to call it
input_schema:
type: object
description: |-
The JSON Schema object for the tool's input parameters
**Notes**:
- `type` must be `object`
- Should declare `properties` and `required`
cache_control:
$ref: '#/components/schemas/CacheControl'
OutputContentBlock:
type: object
description: A content block in the response
properties:
type:
type: string
enum:
- text
- thinking
- tool_use
text:
type: string
description: The text when type=`text`
thinking:
type: string
description: The reasoning-process text when type=`thinking`
signature:
type: string
description: >-
The signature when type=`thinking` (GLM-5.2 may return an empty
string)
id:
type: string
description: The tool call ID when type=`tool_use`
name:
type: string
description: The tool name when type=`tool_use`
input:
type: object
description: >-
The JSON input parameters generated by the model when
type=`tool_use`
AnthropicUsage:
type: object
description: Token usage statistics (Anthropic spec)
properties:
input_tokens:
type: integer
description: Number of input tokens (the portion not served from cache)
example: 18
output_tokens:
type: integer
description: Number of output tokens (including thinking)
example: 101
cache_creation_input_tokens:
type: integer
description: >-
Number of input tokens used for cache creation (always 0 for
GLM-5.2)
example: 0
cache_read_input_tokens:
type: integer
description: >-
Number of input tokens served from cache (when an implicit cache
hits, roughly the length of the shared prefix)
example: 0
prompt_tokens_details:
type: object
description: Input token breakdown (cache-hit fields, also returned by GLM-5.2)
properties:
cached_tokens:
type: integer
description: Number of input tokens served from cache
example: 0
ContentBlock:
type: object
description: |-
Message content block
**Supported types**:
- `text`: text content
- `tool_use`: passes back a previous-turn assistant tool call
- `tool_result`: tool execution result
- `thinking`: passes back previous-turn assistant thinking content
⚠️ Does not support `image` / `video` (text-only model)
required:
- type
properties:
type:
type: string
enum:
- text
- tool_use
- tool_result
- thinking
text:
type: string
description: The text content when type=`text`
id:
type: string
description: Tool call ID (required for tool_use)
name:
type: string
description: Tool name (required for tool_use)
input:
type: object
description: Tool input parameters (for tool_use, a JSON object)
tool_use_id:
type: string
description: >-
The corresponding tool call ID (required for tool_result, filled
back from tool_use.id)
content:
description: >-
Tool execution result (tool_result), a string or an array of content
blocks
oneOf:
- type: string
- type: array
items:
type: object
thinking:
type: string
description: >-
The passed-back assistant thinking-process content (used when
type=`thinking`)
signature:
type: string
description: >-
The signature of the passed-back thinking content, which must be
passed back as-is for multi-turn continuation (GLM-5.2 may return an
empty string)
cache_control:
$ref: '#/components/schemas/CacheControl'
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
##All interfaces require authentication using a Bearer Token##
**Get an API Key**:
Visit the [API Key management page](https://evolink.ai/dashboard/keys)
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`.
````