curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3.8-max",
  "max_tokens": 1024,
  "system": "You are a helpful assistant.",
  "messages": [
    {
      "role": "user",
      "content": "Hello, please introduce yourself"
    }
  ]
}
'

{
  "id": "msg_xxxxxxxx",
  "type": "message",
  "role": "assistant",
  "model": "qwen3.8-max",
  "content": [
    {
      "type": "text",
      "text": "Hello! I am Tongyi Qwen3.8-Max."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 104,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  }
}

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required"
  }
}

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

{
  "type": "error",
  "error": {
    "type": "insufficient_quota",
    "message": "Insufficient credits"
  }
}

{
  "type": "error",
  "error": {
    "type": "<string>",
    "message": "<string>"
  }
}

{
  "type": "error",
  "error": {
    "type": "<string>",
    "message": "<string>"
  }
}

Messages API

Qwen3.8-Max - Anthropic-Compatible API

Call Qwen3.8-Max using the Anthropic Messages protocol
System prompt: set via the top-level system field (not inside messages)
Multimodal input: pass a content block array in content, supporting text / image
Context caching: add cache_control on a content block to declare explicit caching; see usage.cache_read_input_tokens / usage.cache_creation_input_tokens in the response for hit / creation
Thinking mode: enabled via thinking, thinking is returned as thinking content blocks in the stream
Streaming output: when stream=true, returned as Anthropic SSE events (message_start / content_block_delta / message_delta, etc.)

POST

messages

curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3.8-max",
  "max_tokens": 1024,
  "system": "You are a helpful assistant.",
  "messages": [
    {
      "role": "user",
      "content": "Hello, please introduce yourself"
    }
  ]
}
'

{
  "id": "msg_xxxxxxxx",
  "type": "message",
  "role": "assistant",
  "model": "qwen3.8-max",
  "content": [
    {
      "type": "text",
      "text": "Hello! I am Tongyi Qwen3.8-Max."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 104,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  }
}

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required"
  }
}

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

{
  "type": "error",
  "error": {
    "type": "insufficient_quota",
    "message": "Insufficient credits"
  }
}

{
  "type": "error",
  "error": {
    "type": "<string>",
    "message": "<string>"
  }
}

{
  "type": "error",
  "error": {
    "type": "<string>",
    "message": "<string>"
  }
}

BaseURL note: The default BaseURL is https://direct.evolink.ai, which offers better support for text models and long connections. https://api.evolink.ai is the primary multimodal endpoint; use it when your request includes image input.

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>

required

Chat model name

Available options:

qwen3.8-max

Example:

"qwen3.8-max"

max_tokens

integer

required

Maximum number of tokens to generate.

Required (per the Anthropic protocol). Generation will be truncated if the model exceeds this value.

Example:

1024

messages

object[]

required

List of conversation messages (excluding system). Each message contains a role (user / assistant) and content (a string or content block array).

Show child attributes

system

System prompt. Pass a string for plain text; pass a content block array (with cache_control on the block) when declaring explicit caching.

temperature

number

Sampling temperature, range [0, 2].

Required range: 0 <= x <= 2

top_p

number

Nucleus sampling parameter, range (0, 1].

Required range: 0 <= x <= 1

top_k

integer

Sample from the K tokens with the highest probability.

stop_sequences

string[]

Custom stop sequences; generation stops when one is matched.

stream

boolean

default:false

Whether to return an Anthropic SSE event stream.

thinking

object

Deep thinking configuration. When enabled, the model returns its thinking process as thinking content blocks.

Show child attributes

tools

object[]

List of tool definitions (Anthropic tools format) for Function Calling.

Show child attributes

Response

Generated successfully

string

Example:

"msg_xxxxxxxx"

type

string

Example:

"message"

role

string

Example:

"assistant"

model

string

Example:

"qwen3.8-max"

content

object[]

Array of reply content blocks

Show child attributes

stop_reason

string

Stop reason: end_turn (normal completion), max_tokens (limit reached), stop_sequence (stop sequence matched), tool_use (a tool call is required)

Example:

"end_turn"

usage

object

Token usage statistics (Anthropic semantics: input_tokens excludes cache and adds up mutually exclusively with the cache fields).

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Qwen3.8-Max - Anthropic-Compatible API

Authorizations

Body

Response