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

Seed 2.0 Mini API, free to try

Seed 2.0 Mini is the Mini size of the Seed 2.0 model series from ByteDance Seed. It reads text and images and can reason before it answers. 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 262,144-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

Seed 2.0 Mini LLM · Vision

model: "seed-2.0-mini"
reasoning_effort: "none"

system: You read customer e-mails for a support team. Reply with exactly three lines: "Order: <number>", "Date: <YYYY-MM-DD>", "Action: <what the customer asks for, at most 8 words>". No other text.

user

What does this customer want?

Hi,
the standing desk I ordered on 3 November 2026
(order A-48213) arrived with a bent leg.
I don't want a refund. Please send a replacement leg.
Thanks, Marta
assistant

Order: A-48213
Date: 2026-11-03
Action: Send a replacement desk leg

143 input + 31 output tokens (0 reasoning) · 1.2 s Cost on deAPI: $0.00003 (price as of November 2026)

Seed 2.0 Mini 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. Fields from short texts. The e-mail above took 143 input and 31 output tokens with reasoning off. Three runs returned the same order number, date and action. $5 pays for about 170,000 calls of that size.

  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 6.3 seconds (one run), with dates in ISO format and amounts as numbers. A second run returned the same values and wrote the IBAN without spaces.

  3. Sorting tickets and messages. With reasoning_effort set to none, the ticket request from the cURL example below came back as “billing” in 2 output tokens (one run).

  4. Agents that call your functions. Describe a function in tools. Asked “Where is my order A-48213?”, the model called get_order_status with {"order_number": "A-48213"}. Your code runs that call and sends the result 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. 1,605 input + 688 output tokens (559 reasoning), 6.3 s on the first call.

Seed 2.0 Mini 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) $0.11 ≈ 45M tokens
Output (answer and reasoning) $0.44 ≈ 11M tokens
E-mail in the hero, one call $0.00003 ≈ 170,000 calls
Invoice example, one call $0.00048 ≈ 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 seed-2.0-mini in USD, November 2026. Token counts from the hero e-mail and the invoice example. Context and output limits from GET https://oai.deapi.ai/v1/models.

Seed 2.0 Mini vs Seed 2.0 Lite vs Seed 2.0 Pro

Input Text, image Text, image Text, image
Context 262,144 tokens 262,144 tokens 262,144 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 $0.11 / $0.44 $0.275 / $2.20 $0.55 / $3.30

Limits from GET /v1/models, reasoning levels from test calls on 16 November 2026. The three models have the same limits on deAPI and differ in price. At the November 2026 prices, Mini has the lowest input price of the Seed models on deAPI.

Seed 2.0 Mini 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
seed-2.0-mini
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
262,144-token context window, 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": "seed-2.0-mini",
    "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="seed-2.0-mini",
    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 Seed 2.0 Mini?

Seed 2.0 Mini is one of three general-purpose models in the Seed 2.0 series, which ByteDance Seed released on 14 February 2026 in the sizes Pro, Lite and Mini. ByteDance describes Mini as “optimized for inference throughput and deployment density” and “designed for high concurrency and batch generation scenarios”. On deAPI it reads text and images, writes text, and can reason before it answers. 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 seed-2.0-mini as the model and read the answer from choices[0].message.content.

Seed 2.0 Mini FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID seed-2.0-mini, with the request and response format of the OpenAI Chat Completions API. In code written for 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 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.
$0.11 per million input tokens and $0.44 per million output tokens (November 2026). At those prices it has the lowest input price of the Seed models on deAPI. 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 262,144 tokens and one answer can be up to 131,072 tokens long. A request with max_tokens set to 131,073 was rejected with an invalid_request_error.
Set reasoning_effort to none. On the ticket request from the cURL example, none answered “billing” with 2 output tokens. high gave the same answer with 25 output tokens, 23 of them reasoning (one run each). If you leave the parameter out, the model may still reason: the invoice example was sent without it and used 559 reasoning tokens.
ByteDance Seed calls it Seed2.0 Mini on its Seed 2.0 page. The Volcano Engine model list carries it under the ID doubao-seed-2-0-mini. On deAPI the model ID is seed-2.0-mini.
On deAPI all three take text and images, share a 262,144-token context window and differ in price. ByteDance describes Pro as focused on “long-chain reasoning and robustness in complex workflows”, Lite as a balance of “output quality and response speed”, and Mini as built for high concurrency and batch generation. Run the same prompts on each with the free credits and compare the answers.

Send your first Seed 2.0 Mini request with $5 of free credits

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