GPT 2.6, Veo 3.1, Seedance 2.5, Kling 4 in deAPI!
Web-search and web-contents are now available via API
Browse all Models
Browse all
Browse all
Browse all

LLM · Vision

Qwen3.8 Max API, free to try

Qwen3.8 Max is the flagship large language model of Alibaba’s Qwen series, announced in August 2026. It reads text and images, reasons before it answers and holds up to 1M tokens of context. deAPI serves it on an OpenAI-compatible endpoint, so the OpenAI SDK works once you change the base URL, the key and the model ID.

  • Text and images in, a 1,000,000-token context window
  • JSON schema output, tool calls and streaming
  • reasoning_effort in seven levels, from none to max

No credit card · Free credits valid for 30 days · Then top up and pay as you go, no subscription

Qwen3.8 Max LLM · Vision

model: "qwen3.8-max"
reasoning_effort: "low"

system: You are a senior SQL engineer. Explain in two sentences, then give the fixed query.

user

Why are customers with no orders missing from the result?

SELECT c.name, COUNT(o.id) AS orders
FROM customers c
LEFT JOIN orders o ON o.customer_id = c.id
WHERE o.created_at >= '2026-01-01'
GROUP BY c.name;
assistant reasoning_content · 165 tokens

The WHERE clause filters after the join, so when a customer has no orders, o.created_at is NULL and the condition evaluates to UNKNOWN, discarding that row. Move the date filter into the ON clause so it only restricts which orders get matched, preserving unmatched customers.

SELECT c.name, COUNT(o.id) AS orders
FROM customers c
LEFT JOIN orders o
       ON o.customer_id = c.id
      AND o.created_at >= '2026-01-01'
GROUP BY c.name;
126 input + 292 output tokens (165 reasoning) · 9.0 s Cost on deAPI: $0.0022 (price as of November 2026)

Qwen3.8 Max use cases

Four jobs where the model fits, each with the number behind it. All of them run on the same deAPI key as transcription, OCR and image generation.

  1. Invoices, receipts and forms. Send a photo or scan as image_url with a JSON schema. On the generated German invoice below it returned all 10 fields in both of two runs, with dates in ISO format and amounts as numbers. The first run took 10.8 seconds.

  2. Coding agents. Alibaba’s model card reports 86.6 on Terminal Bench 2.1 (Claude Code harness, average of 10 runs) and 67.7 on SWE-bench Pro (Claude Code harness). Coding tools that speak the OpenAI Chat Completions API can point at https://oai.deapi.ai/v1.

  3. Long transcripts and documents. The context window holds 1,000,000 tokens, prompt and answer together, and one answer can run to 131,072. Alibaba reports 92.9 on MRCR v2 (256K, 8-needle), a long-context retrieval test. Transcribe a day of sales calls with WhisperLargeV3Ct2 and ask for objections, follow-ups and quotes in one request.

  4. Agents that call deAPI. Describe deAPI endpoints as tools. Asked for chapters of a YouTube video, the model called transcribe_video with include_ts: true (one run). Your code runs that call and sends the transcript back.

German invoice from Nordlicht Studio GmbH with three line items and a total of 2,677.50 EUR
Response: message.content
{
  "invoice_number": "NS-2026-0418",
  "issue_date": "2026-11-03",
  "due_date": "2026-11-17",
  "seller": "Nordlicht Studio GmbH",
  "seller_vat_id": "DE298765431",
  "net": 2250.0,
  "vat": 427.5,
  "total": 2677.5,
  "currency": "EUR",
  "iban": "DE44 1001 0010 0123 4567 89"
}
Invoice example: image in, JSON out System: “Extract invoice fields. Dates as YYYY-MM-DD, amounts as numbers.” User: “Extract the fields from this invoice.” JSON schema with 10 fields, temperature 0. 1,070 input + 394 output tokens (222 reasoning), 10.8 s on the first call.

Qwen3.8 Max API pricing

You pay per token from the same prepaid balance as every other deAPI model. Reasoning tokens are part of completion_tokens in usage. No subscription.

Input (text and images) $2.20 ≈ 2.2M tokens
Cached input (repeated prompt prefix) $0.275 ≈ 18M tokens
Output (answer and reasoning) $6.60 ≈ 0.7M tokens
Question in the hero, one call $0.0022 ≈ 2,200 calls
Invoice example, one call $0.005 ≈ 1,000 calls

What the free account includes

  • $5 of credits once you add a payment card
  • About 1,000 calls like the invoice example
  • Credits valid for 30 days, then top up and pay as you go
Get $5 credits

Prices for qwen3.8-max in USD, November 2026. Token counts from the hero question and the invoice example. Context and output limits from GET https://oai.deapi.ai/v1/models.

Qwen3.8 Max vs Qwen3.8 Flash vs Kimi K3

Input Text, image Text, image Text, image
Context 1,000,000 tokens 1,000,000 tokens 1,000,000 tokens
Max output 131,072 tokens 131,072 tokens 131,072 tokens
reasoning_effort none to max, 7 levels none to max, 7 levels none to max, 7 levels
Price per 1M, input / output $2.20 / $6.60 $0.165 / $0.517 $3.30 / $16.50

Inputs and limits from GET /v1/models. Each reasoning_effort level was sent to each model once on 16 November 2026 and accepted. Prices in USD, November 2026.

Qwen3.8 Max API example

One POST to https://oai.deapi.ai/v1/chat/completions with your deAPI key as the Bearer token. In the OpenAI SDK, set base_url, your deAPI key and the model ID; the rest of a Chat Completions call stays the same. Replace YOUR_API_KEY with a key from your dashboard.

Model ID
qwen3.8-max
Endpoint
POST https://oai.deapi.ai/v1/chat/completions
Input
Text and images as image_url parts: a base64 data URL or a public HTTPS link. PDFs and audio are rejected.
Context and output
1,000,000-token context window (prompt and answer together), up to 131,072 tokens per answer
Reasoning
reasoning_effort: none, minimal, low, medium, high, xhigh or max. The reasoning comes back in reasoning_content, and reasoning tokens count toward max_tokens.
Output options
response_format with json_schema (strict) or json_object, tools, stream
curl https://oai.deapi.ai/v1/chat/completions \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen3.8-max",
    "reasoning_effort": "none",
    "messages": [
      {"role": "system", "content": "Sort support tickets. Reply with one word: billing, bug, feature or other."},
      {"role": "user", "content": "I was charged twice for the November top-up."}
    ]
  }'
import base64, json
from openai import OpenAI

client = OpenAI(base_url="https://oai.deapi.ai/v1", api_key="YOUR_API_KEY")

with open("invoice.png", "rb") as f:
    image = "data:image/png;base64," + base64.b64encode(f.read()).decode()

schema = {
    "type": "object",
    "additionalProperties": False,
    "required": ["invoice_number", "issue_date", "due_date", "seller",
                 "seller_vat_id", "net", "vat", "total", "currency", "iban"],
    "properties": {
        "invoice_number": {"type": "string"},
        "issue_date": {"type": "string"},
        "due_date": {"type": "string"},
        "seller": {"type": "string"},
        "seller_vat_id": {"type": "string"},
        "net": {"type": "number"},
        "vat": {"type": "number"},
        "total": {"type": "number"},
        "currency": {"type": "string"},
        "iban": {"type": "string"},
    },
}

response = client.chat.completions.create(
    model="qwen3.8-max",
    temperature=0,
    messages=[
        {"role": "system", "content": "Extract invoice fields. "
         "Dates as YYYY-MM-DD, amounts as numbers."},
        {"role": "user", "content": [
            {"type": "text", "text": "Extract the fields from this invoice."},
            {"type": "image_url", "image_url": {"url": image}},
        ]},
    ],
    response_format={"type": "json_schema",
                     "json_schema": {"name": "invoice", "strict": True, "schema": schema}},
)

invoice = json.loads(response.choices[0].message.content)
print(invoice["total"], invoice["currency"])  # 2677.5 EUR
print(response.usage)

What is Qwen3.8 Max?

Qwen3.8 Max is a sparse Mixture-of-Experts model that Alibaba announced on 3 August 2026 as the most capable model in its Qwen series. Alibaba gives its size as 2.4 trillion parameters, of which 95 billion are active per token. It reads text and images, writes text, and can reason before it answers. On deAPI you call it like any OpenAI chat model and pay per token.

  1. Create a free account

    Sign up and get $5 of credits.

  2. Point your client at deAPI

    Set base_url to https://oai.deapi.ai/v1 and use your deAPI key.

  3. Send the request

    Use qwen3.8-max as the model and read the answer from choices[0].message.content.

Qwen3.8 Max FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID qwen3.8-max, with the request and response format of the OpenAI Chat Completions API. If your code already uses the OpenAI SDK, you change three values: base_url, the API key and the model. Run your own tests before you switch traffic.
A new deAPI account gets $5 of credits once you add a payment card, enough for about 1,000 calls like the invoice example on this page. The credits are valid for 30 days. After that you top up and pay as you go, with no subscription.
$2.20 per million input tokens and $6.60 per million output tokens (November 2026). Reasoning tokens count as output, and you see them in usage.completion_tokens_details.reasoning_tokens.
Yes. Add an image_url part to the user message, as a base64 data URL or a public HTTPS link. PDFs and audio files are rejected: run PDFs through the OCR API or send pages as images, and transcribe audio first.
On deAPI the context window is 1,000,000 tokens, prompt and answer together, and one answer can be up to 131,072 tokens long. A larger max_tokens is rejected with an error.
Alibaba’s model card lists 92.6 on GPQA Diamond, 86.6 on Terminal Bench 2.1 and 67.7 on SWE-bench Pro (both with the Claude Code harness), 82.8 on IFBench and 92.9 on MRCR v2 (256K, 8-needle). These are Alibaba’s numbers; test it on your own data with the free credits.
Set reasoning_effort to none. On the ticket request from the cURL example, none answered “billing” with 1 output token. high gave the same answer with 63 output tokens, 59 of them reasoning (one run each). The levels in between are minimal, low and medium; above high come xhigh and max.
Alibaba publishes the weights of Qwen3.8-2.4T-A95B, the text-only checkpoint Qwen3.8 Max is based on, on Hugging Face under its own Qwen3.8-Max License. That license allows commercial use and adds conditions for large services, so read it before you host the weights yourself. Calls through deAPI are covered by the deAPI Terms of Service.

Send your first Qwen3.8 Max request with $5 of free credits

Sign up with e-mail or Google. No subscription, pay as you go.