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 Pro API, free to try

Seed 2.0 Pro is a large language model from ByteDance Seed that can reason before it answers. It reads text and images and holds up to 262,144 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 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 Pro LLM · Vision

model: "seed-2.0-pro"
reasoning_effort: "high"

system: You are a careful analyst. Give the result first, then two sentences of working. Plain text, no Markdown, no LaTeX.

user

A batch has 1,800 audio files that average 4 minutes 30 seconds each. One worker transcribes 12 times faster than real time, and 6 workers run in parallel. How long does the batch take?

assistant reasoning_content · 963 tokens

112.5 minutes (or 1 hour 52 minutes 30 seconds).
First, calculate total audio duration: 1800 files multiplied by 4.5 minutes per file gives 8100 total minutes of audio.
Next, the combined transcription rate is 6 workers times 12 audio minutes per real minute, so dividing total audio by 72 gives 112.5 minutes of real time.

112 input + 1,058 output tokens (963 reasoning) · 23.9 s Cost on deAPI: $0.0036 (price as of November 2026)

Seed 2.0 Pro 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. ByteDance reports 93.5 on CharXiv-DQ and 78.2 on MMMU-Pro for Seed2.0 Pro (0215).

  2. Multi-step calculations. The scheduling question in the hero came back correct in three of three runs at reasoning_effort: high. ByteDance reports 88.9% on GPQA Diamond and 86.5% on BeyondAIME for Seed2.0 Pro (0215).

  3. Long transcripts and documents. The context window holds 262,144 tokens, prompt and answer together, and one answer can run to 131,072. Transcribe a batch of sales calls with WhisperLargeV3Ct2 and ask for objections, follow-ups and quotes in one request.

  4. Agents that call tools. ByteDance reports 77.3% on BrowseComp, 46.9% on SWE-Bench Pro and 55.8% on Terminal Bench 2.0 for Seed2.0 Pro (0215). Asked for chapters of a YouTube video with a transcribe_video tool defined, the model called it with include_ts: true. 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 Prompt: “Extract the fields from this invoice.” System message: “Extract invoice fields. Dates as YYYY-MM-DD, amounts as numbers.” JSON schema with 10 fields, temperature 0. 1,605 input + 445 output tokens, 8.9 s on the first call.

Seed 2.0 Pro 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) $0.55 ≈ 9.0M tokens
Cached input (repeated prompt prefix) $0.11 ≈ 45M tokens
Output (answer and reasoning) $3.30 ≈ 1.5M tokens
Question in the hero, one call $0.0036 ≈ 1,400 calls
Invoice example, one call $0.0024 ≈ 2,100 calls

What the free account includes

  • $5 of credits once you add a payment card
  • About 2,100 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-pro 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.

Seed 2.0 Pro vs Seed 2.0 Lite vs Seed 2.1 Turbo

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 262,144 tokens
reasoning_effort none to max, 7 levels none to max, 7 levels none to max, 7 levels
Price per 1M, input / output $0.55 / $3.30 $0.275 / $2.20 $0.55 / $2.75

Limits and input types from GET /v1/models. Each reasoning_effort level was sent to each model once on 16 November 2026 and accepted.

Seed 2.0 Pro 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-pro
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 (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.
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-pro",
    "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="seed-2.0-pro",
    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 Pro?

Seed 2.0 Pro is the Pro model of the Seed 2.0 series, which ByteDance Seed launched on 14 February 2026 together with Seed 2.0 Lite and Mini. ByteDance describes it as focused on long-chain reasoning and robustness in complex workflows. At launch it went into the Doubao app and TRAE, and Volcano Engine lists it as doubao-seed-2-0-pro. On deAPI it reads text and images, writes text, and 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-pro as the model and read the answer from choices[0].message.content.

Seed 2.0 Pro FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID seed-2.0-pro, 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 2,100 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.
$0.55 per million input tokens and $3.30 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 262,144 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.
ByteDance’s model page lists these scores for Seed2.0 Pro (0215): 88.9% on GPQA Diamond, 68.7% on SuperGPQA, 46.9% on SWE-Bench Pro, 55.8% on Terminal Bench 2.0 and 77.3% on BrowseComp. For images it lists 78.2 on MMMU-Pro and 88.8 on MathVision. These are ByteDance’s numbers for that snapshot, and deAPI’s model list does not name a snapshot; 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 2 output tokens. high gave the same answer with 38 output tokens, 36 of them reasoning (one run each). On the scheduling question in the hero, high was correct in three of three runs and low in two of three, so for that question high was the safer setting.
ByteDance Seed calls the model Seed2.0 Pro, and Volcano Engine lists it as doubao-seed-2-0-pro. ByteDance’s launch post offers it through the Doubao app, TRAE and an API and links no weight download. Calls through deAPI are covered by the deAPI Terms of Service.

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

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