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 Lite API, free to try

Seed 2.0 Lite is one of three general-purpose models in ByteDance Seed’s Seed 2.0 series, next to Pro and Mini. It reads text and images, can reason before it answers, 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 Lite LLM · Vision

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

system: You write product copy for an online shop. Turn the note into a product description of exactly two sentences, 45 words at most. Keep every fact and add none. Plain text only.

user

Rewrite this note for the product page.

steel bottle 750 ml, double wall
cold 24 h / hot 12 h
bottle fits car cup holder, lid doesnt leak
colors: black, sage, sand
dishwasher: lid only, bottle by hand
assistant

This 750 ml double-wall steel bottle keeps drinks cold 24 hours and hot 12 hours, fits car cup holders, has a leakproof lid, and comes in black, sage, and sand. Hand-wash the bottle, only the lid is dishwasher safe.

137 input + 58 output tokens (0 reasoning) · 3.0 s Cost on deAPI: $0.00017 (price as of November 2026)

Seed 2.0 Lite 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. Product copy from rough notes. The request above turned a five-line note into a two-sentence description in three runs out of three. Each answer kept every fact and stayed under the 45-word limit. One call used 137 input and 58 output tokens with reasoning off, so $5 covers about 30,000 of them.

  2. Customer messages. The cURL example below translates a lowercase German order question into clean English and keeps the order number. With reasoning off it used 83 input and 36 output tokens (one run): $0.0001 per message.

  3. 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 correctly in both of two runs, with dates in ISO format and amounts as numbers.

  4. Charts and screenshots. For Seed2.0 Lite (0428), ByteDance Seed reports 94.5 on CharXiv-DQ and 82.4 on CharXiv-RQ in its infographics tests, and 64.4% on OSWorld-Verified for GUI tasks. On deAPI you send the chart or screenshot as an image_url part.

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, <code>reasoning_effort</code> not set. 1,605 input + 415 output tokens (270 of them reasoning), 8.8 s on the first call.

Seed 2.0 Lite 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) $0.275 ≈ 18M tokens
Output (answer and reasoning) $2.20 ≈ 2.2M tokens
Product note in the hero, one call $0.00017 ≈ 30,000 calls
Invoice example, one call $0.0014 ≈ 3,600 calls

What the free account includes

  • $5 of credits once you add a payment card
  • About 3,600 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-lite in USD, November 2026. Token counts from the hero request and the invoice example. Context and output limits from GET https://oai.deapi.ai/v1/models.

Seed 2.0 Lite vs Seed 2.0 Mini vs Seed 2.0 Pro

Model ID seed-2.0-lite seed-2.0-mini 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 $0.275 / $2.20 $0.11 / $0.44 $0.55 / $3.30

Limits and input types from GET /v1/models; reasoning_effort levels tested on 16 November 2026. On deAPI the three models have the same limits and differ in price. ByteDance Seed describes Pro as the model for long-chain reasoning, Lite as the general-purpose one and Mini as the one for high concurrency and batch generation.

Seed 2.0 Lite 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-lite
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. Without the parameter the model reasons. 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-lite",
    "reasoning_effort": "none",
    "messages": [
      {"role": "system", "content": "Translate the customer message into English and fix the grammar. Reply with the translation only."},
      {"role": "user", "content": "hallo, hab am montag bestellt (nr 48213) aber noch keine versandmail bekommen?? brauche das paket bis freitag"}
    ]
  }'
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-lite",
    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 Lite?

Seed 2.0 Lite is one of the three general-purpose agent models in the Seed 2.0 series, which ByteDance Seed launched on 14 February 2026. ByteDance Seed describes Lite as the model that balances output quality and response speed, and upgraded it at the end of April (version 0428). Pro is aimed at long-chain reasoning, Mini at high concurrency and batch generation. On deAPI Seed 2.0 Lite 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-lite as the model and read the answer from choices[0].message.content.

Seed 2.0 Lite FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID seed-2.0-lite, 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 3,600 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.
$0.275 per million input tokens and $2.20 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. Seed 2.0 Mini and Seed 2.0 Pro have the same limits.
ByteDance Seed publishes results for two versions of Lite on its Seed 2.0 page. For Seed2.0 Lite (0428): 88.4% on GPQA Diamond, 46.6% on SWE-Bench Pro, 78.4 on MMMU_Pro and 94.5 on CharXiv-DQ. For Seed2.0 Lite (0215): 85.1%, 46.0%, 76.0 and 93.3. These are ByteDance Seed’s numbers, and deAPI’s model list does not name a version; test the model on your own data with the free credits.
Set reasoning_effort to none. On the request from the cURL example, none returned the translation in 36 output tokens. high returned nearly the same sentence in 307 output tokens, 271 of them reasoning (one run each). If you leave the parameter out, the model reasons: the invoice call spent 270 of its 415 output tokens on reasoning.
On deAPI both read text and images and share the same context window, output limit and reasoning_effort levels. Lite costs $0.275 / $2.20 per million input / output tokens, Pro $0.55 / $3.30. ByteDance Seed positions Pro for long-chain reasoning in complex workflows and Lite as the general-purpose production model. To compare them, send the same prompts to both and change only the model ID.

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

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