qwen3.8-max Integration Guide

curl --request POST \
  --url https://api.apimart.ai/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.apimart.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.apimart.ai/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.apimart.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

POST

chat

completions

qwen3.8-max Integration Guide

curl --request POST \
  --url https://api.apimart.ai/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.apimart.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.apimart.ai/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.apimart.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

OpenAI SDK compatible: swap base_url and api_key. Model name is fixed qwen3.8-max.

from openai import OpenAI

client = OpenAI(
    api_key="<your APIMart key>",
    base_url="https://api.apimart.ai/v1",
)

resp = client.chat.completions.create(
    model="qwen3.8-max",
    messages=[{"role": "user", "content": "Describe Hangzhou in one sentence"}],
    stream=False,  # must set explicitly — see below
)
print(resp.choices[0].message.content)

Related APIs:

Three easy pitfalls

1. `/v1/chat/completions` defaults to streaming if `stream` is omitted

# Omitting stream → SSE; parsing as non-stream fails
client.chat.completions.create(model="qwen3.8-max", messages=[...])

# Non-stream requires explicit False
client.chat.completions.create(
    model="qwen3.8-max",
    messages=[...],
    stream=False,
)

This is opposite to OpenAI’s default (omit = non-stream). Easy to miss when porting SDK code.

2. Built-in tools work only on `/v1/responses`

/v1/chat/completions does not support built-in tools (they are ignored with no error). For web search, code interpreter, text-to-image search, or image-to-image search, use the Responses API.

3. Wrong tool names fail silently

Invalid tool names are accepted quietly. t2i_search / i2i_search on pricing pages are not valid tool names:

Name you may see	Actual tool type
`t2i_search` (pricing UI)	`web_search_image`
`i2i_search` (pricing UI)	`image_search`

Built-in tools (Responses)

Declare in /v1/responses tools as {"type": "<name>"}.

Tool	Purpose	Constraints
`web_search`	Search the web and cite	—
`web_extractor`	Fetch page body by URL	Must be declared with `web_search`; alone → 400
`code_interpreter`	Run code in a sandbox	—
`web_search_image`	Text→image search (existing web images, not generation)	—
`image_search`	Image→image search	Provide an image in `input`; slower — prefer streaming

Web search

resp = client.responses.create(
    model="qwen3.8-max",
    input="One sentence about Shanghai weather tomorrow",
    tools=[{"type": "web_search"}],
    max_output_tokens=600,
)

Web extract

resp = client.responses.create(
    model="qwen3.8-max",
    input="Fetch https://example.com and summarize the first screen",
    tools=[
        {"type": "web_search"},
        {"type": "web_extractor"},  # missing web_search → 400
    ],
)

Typical error text:

The web_extractor tool must be executed with web_search tool.

Image search

resp = client.responses.create(
    model="qwen3.8-max",
    input=[{
        "role": "user",
        "content": [
            {"type": "input_image", "image_url": "https://example.com/your.jpg"},
            {"type": "input_text", "text": "Find similar images"},
        ],
    }],
    tools=[{"type": "image_search"}],
    stream=True,  # recommended: this tool is noticeably slower
)

Confirm a tool was called

Trust usage.x_tools (billing source of truth):

{
  "output": [
    { "type": "reasoning" },
    { "type": "web_search_call" },
    {
      "type": "message",
      "content": [{ "type": "output_text", "text": "..." }]
    }
  ],
  "usage": {
    "input_tokens": 2528,
    "output_tokens": 362,
    "output_tokens_details": { "reasoning_tokens": 280 },
    "x_tools": { "web_search": { "count": 1 } }
  }
}

Tools declared but not invoked are free — they do not appear in x_tools.

Thinking (reasoning)

Thinking cannot be turned off. Every request reasons before answering:

Thinking tokens bill as output, via output_tokens_details.reasoning_tokens
Responses: reasoning items in output; chat stream: delta.reasoning_content
enable_thinking: false is ignored in stream mode; non-stream is degraded — not recommended

Output token usage with thinking is often much higher. Cap cost with max_output_tokens.

Context cache

Reuse long prompts to cut input cost.

Implicit cache (automatic)

Repeated requests with the same prefix may hit cache from the second call; hits bill at cache rates (~1/8 of normal input). Hit size is block-rounded; full hit is not guaranteed.

Explicit cache

Mark content with cache_control:

client.chat.completions.create(
    model="qwen3.8-max",
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": "<long fixed context>",
                    "cache_control": {"type": "ephemeral"},
                }
            ],
        },
        {"role": "user", "content": "Answer based on the context above"},
    ],
    stream=False,
)

Item	Notes
Min cache content	≥ 1024 tokens
TTL	5 minutes
Cache create	Slightly more expensive than normal input
Explicit hit	Usually cheaper than implicit hit

Response distinction:

// create
"prompt_tokens_details": {
  "cache_creation_input_tokens": 1482,
  "cache_type": "ephemeral",
  "cached_tokens": 0
}

// hit
"prompt_tokens_details": {
  "cache_creation_input_tokens": 0,
  "cache_type": "ephemeral",
  "cached_tokens": 1482
}

Implicit hits typically only set cached_tokens (may omit cache_type: "ephemeral").

PDF understanding

Supported only on /v1/chat/completions. Responses silently ignores PDFs (no error).

client.chat.completions.create(
    model="qwen3.8-max",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "file",
                "file": {"file_url": "https://example.com/doc.pdf"},
            },
            # or base64:
            # {"type": "file", "file": {"file_data": "data:application/pdf;base64,...", "filename": "doc.pdf"}}
            {"type": "text", "text": "What is this document about?"},
        ],
    }],
    stream=False,
)

PDFs are understood as images and bill as image input tokens (~letter ~2082 tok/page, A4 ~2147 tok/page order of magnitude); no extra parse fee
fileid:// is invalid here (other-model mechanism) and treated as plain text

Billing model

Total = token fees + per-call tool fees (independent).

Item	How billed
Input	Per token; cache hits use cache rates
Output	Per token; thinking counts as output
Built-in tools	Actual calls in `usage.x_tools` (often priced per 1000 calls)

Fetch unit prices via the pricing API:

GET /api/pricing/model?model=qwen3.8-max

Read data.pricing.effective_rates (includes group discount) and data.pricing.extras.tools.

Limits

Item	Value
Max input	983,616 tokens (~1M)
Max output	131,072 tokens
Cache read / write	Supported / supported
Multimodal input	Images, video, etc. (e.g. `input_image`)

FAQ

Q: I passed tools but nothing ran?
① Use /v1/responses; ② correct tool names (not t2i_search); ③ check usage.x_tools — missing means not invoked and not billed. Q: web_extractor returns 400?
Declare it together with web_search. Q: Non-stream is slow?
Tool calls (especially image_search) take longer. Prefer streaming when timeouts matter. Q: Can I disable thinking to save money?
No. Cap with max_output_tokens, or switch to a model that allows disabling thinking. Q: How do I check usage?

GET /v1/dashboard/billing/usage
GET /v1/dashboard/billing/subscription

Visión general

Modelos

Serie de texto

Serie de imágenes

Serie de video

Serie de audio

Serie de Moderación

Gestión de subidas

Gestión de tareas

Gestión de cuenta

qwen3.8-max Integration Guide

Three easy pitfalls

1. `/v1/chat/completions` defaults to streaming if `stream` is omitted

2. Built-in tools work only on `/v1/responses`

3. Wrong tool names fail silently

Built-in tools (Responses)

Web search

Web extract

Image search

Confirm a tool was called

Thinking (reasoning)

Context cache

Implicit cache (automatic)

Explicit cache

PDF understanding

Billing model

Limits

FAQ

​Three easy pitfalls

​1. /v1/chat/completions defaults to streaming if stream is omitted

​2. Built-in tools work only on /v1/responses

​3. Wrong tool names fail silently

​Built-in tools (Responses)

​Web search

​Web extract

​Image search

​Confirm a tool was called

​Thinking (reasoning)

​Context cache

​Implicit cache (automatic)

​Explicit cache

​PDF understanding

​Billing model

​Limits

​FAQ

Three easy pitfalls

1. `/v1/chat/completions` defaults to streaming if `stream` is omitted

2. Built-in tools work only on `/v1/responses`

3. Wrong tool names fail silently

Built-in tools (Responses)

Web search

Web extract

Image search

Confirm a tool was called

Thinking (reasoning)

Context cache

Implicit cache (automatic)

Explicit cache

PDF understanding

Billing model

Limits

FAQ