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 Flash API, free to try

Qwen3.8 Flash is a multimodal large language model from Alibaba’s Qwen team that can reason. It reads text and images 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 Flash LLM · Vision

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

system: You moderate product reviews for a marketplace. Harsh criticism of a product is allowed. Insults aimed at people, contact details and offers to pay outside the checkout are not. Reply with ALLOW, REVIEW or REMOVE, then one sentence with the reason.

user

Review: "This charger killed my phone in two days. Absolute garbage, do not buy."

assistant reasoning_content · 124 tokens

ALLOW — The review contains harsh but permissible criticism of the product itself, with no personal insults, contact details, or off-platform payment offers.

111 input + 155 output tokens (124 reasoning) · 2.7 s Cost on deAPI: $0.0001 (price as of November 2026)

Qwen3.8 Flash 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. Moderation and ticket triage. Put your rules in the system message and ask for a verdict with a reason. The review above got ALLOW in all three runs; run 1 cost $0.0001. A one-word ticket label with reasoning_effort: none took 44 input tokens and 1 output token.

  2. 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 runs, with dates in ISO format and amounts as numbers.

  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. 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": 2250.00,
  "vat": 427.50,
  "total": 2677.50,
  "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. 1,108 input + 534 output tokens, 7.8 s on the first call. The second call returned the same values with 1,240 output tokens.

Qwen3.8 Flash 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) $0.165 ≈ 30M tokens
Cached input (repeated prompt prefix) $0.0176 ≈ 284M tokens
Output (answer and reasoning) $0.517 ≈ 9.6M tokens
Review in the hero, one call $0.0001 ≈ 50,000 calls
Invoice example, one call $0.00046 ≈ 10,000 calls

What the free account includes

  • $5 of credits once you add a payment card
  • About 10,000 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-flash in USD, November 2026. Token counts from the hero review and the first invoice call. Context and output limits from GET https://oai.deapi.ai/v1/models.

Qwen3.8 Flash vs DeepSeek V4.1 Flash vs GLM-5.3 Flash

Input Text, image Text, image Text, image
Context 1,000,000 tokens 1,048,576 tokens 1,048,576 tokens
Max output 131,072 tokens 393,216 tokens 131,072 tokens
reasoning_effort none to max, 7 levels none to max, 7 levels none to max, 7 values; reasons even at none
Invoice example: input tokens 1,108 782 1,440
Invoice example: fields correct, run 1 / run 2 10 of 10 / 10 of 10 10 of 10 / 10 of 10 10 of 10 / 9 of 10 (IBAN without spaces; one digit missing in run 2)
Price per 1M, input / output $0.165 / $0.517 $0.132 / $0.528 $0.165 / $0.55

Two calls per model in one session on 16 November 2026: same image, prompt and JSON schema, temperature 0. Model IDs: qwen3.8-flash, deepseek-v4.1-flash:economy, glm-5.3-flash. Limits from GET /v1/models.

Qwen3.8 Flash 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-flash
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. 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-flash",
    "reasoning_effort": "low",
    "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-flash",
    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 Flash?

Qwen3.8 Flash is a multimodal Mixture-of-Experts model that Alibaba announced in August 2026 as an early preview of the architecture planned for the Qwen4 series. Alibaba describes a 125B-parameter main model with 51B of n-gram embeddings and 6B parameters active per token. The open weights are published as Qwen3.8-Flash-Next, and Qwen calls Qwen3.8-Flash the official version based on it. 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-flash as the model and read the answer from choices[0].message.content.

Qwen3.8 Flash FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID qwen3.8-flash, with the request and response format of the OpenAI Chat Completions API. If you already call the model through an OpenAI-compatible client, you change three values in most code: 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 10,000 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.
$0.165 per million input tokens and $0.517 per million output tokens (November 2026). Reasoning tokens count as output, and you see them in usage.completion_tokens_details.reasoning_tokens. Cached input costs $0.0176 per million: on the second identical invoice call, usage reported 1,024 of the 1,108 input tokens as cached.
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. Alibaba Cloud lists the same two limits for its own qwen3.8-flash API.
Qwen publishes scores for the open-weight Qwen3.8-Flash-Next on its model card: 62.5 on SWE-bench Pro, 91.9 on LiveCodeBench v6, 91.7 on GPQA Diamond, 88.5 on RealWorldQA and 84.5 on AndroidWorld. These are Qwen’s numbers, measured with the harnesses and settings listed on the card. Test the model 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 73 output tokens, 69 of them reasoning (one run each). The levels in between are minimal, low and medium; above high come xhigh and max.
Qwen publishes open weights as Qwen3.8-Flash-Next on Hugging Face under the Qwen Community License 1.0, and describes Qwen3.8-Flash as the official version based on it. Read that license before you build a product on the weights. Calls through deAPI are covered by the deAPI Terms of Service.

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

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