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 2.1 Turbo API, free to try

Seed 2.1 Turbo is one of the two Seed2.1 models from ByteDance Seed, the one designed for high-throughput products. It reads text and images, can reason before it answers and holds 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 2.1 Turbo LLM · Vision

model: "seed-2.1-turbo"
reasoning_effort: "low"

system: You write 5-field cron expressions. Reply with the expression in a code block, then one sentence with the main caveat.

user

Run the report every weekday at 7:30, except in August.

assistant reasoning_content · 409 tokens
30 7 * 1-7,9-12 1-5

This follows standard 5-field cron conventions where weekday values 1 through 5 map to Monday through Friday, and no runs will be scheduled at all during the 8th calendar month (August).

78 input + 472 output tokens (409 reasoning) · 8.8 s Cost on deAPI: $0.0013 (price as of November 2026)

Seed 2.1 Turbo 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. Tool calls for agents and support bots. Given three billing tools and the message “Invoice NS-2026-0418 was paid twice. Refund the second payment of 2,677.50 EUR.”, the model called issue_refund with the invoice number, 2677.5 and EUR in both of two runs. ByteDance Seed reports 80.3 on MCP-Atlas for Seed2.1 Turbo.

  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 correctly in both of two runs, with dates in ISO format and amounts as numbers. ByteDance Seed reports 82.5 on CharXiv-RQ and 80.1 on MMMU-Pro, both without tools.

  3. Schedules, routing and other short answers. In three runs of the question in the hero the model returned the same cron expression, 30 7 * 1-7,9-12 1-5. With reasoning_effort: none it sorted a support ticket with 60 input and 2 output tokens, $0.00004 for the call.

  4. Long transcripts and documents. The context window holds 262,144 tokens. Transcribe a recorded meeting with WhisperLargeV3Ct2 and ask for decisions, owners and deadlines in one request. ByteDance Seed reports 76.9 on MMLongBench-128K.

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. 1,602 input + 348 output tokens (222 reasoning), 7.9 s on the first call.

Seed 2.1 Turbo 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) $2.75 ≈ 1.8M tokens
Question in the hero, one call $0.0013 ≈ 3,700 calls
Invoice example, one call $0.0018 ≈ 2,700 calls

What the free account includes

  • $5 of credits once you add a payment card
  • About 2,700 calls like the invoice example
  • Credits valid for 30 days, then top up and pay as you go
Get $5 credits

Prices for seed-2.1-turbo 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 2.1 Turbo vs Seed 2.0 Pro vs Qwen3.8 Flash

Input Text, image Text, image Text, image
Context 262,144 tokens 262,144 tokens 1,000,000 tokens
Max output 262,144 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 $0.55 / $2.75 $0.55 / $3.30 $0.165 / $0.517

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

Seed 2.1 Turbo 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-2.1-turbo
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 262,144 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-2.1-turbo",
    "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", "description": "ISO 8601"},
        "due_date": {"type": "string", "description": "ISO 8601"},
        "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-2.1-turbo",
    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 2.1 Turbo?

Seed 2.1 Turbo is one of the two models in ByteDance Seed’s Seed2.1 family; the other is Seed2.1 Pro. ByteDance Seed announced the Seed2.1 family on 23 June 2026. ByteDance Seed’s model card describes Turbo as designed for efficient, high-throughput product scenarios and Pro as the model for stronger reasoning. On Doubao and Volcano Engine the family is called Doubao Seed 2.1, and BytePlus lists this model as dola-seed-2-1-turbo. 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-2.1-turbo as the model and read the answer from choices[0].message.content.

Seed 2.1 Turbo FAQ

Yes. deAPI serves it at https://oai.deapi.ai/v1 under the model ID seed-2.1-turbo, 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 2,700 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 $2.75 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, and the output limit listed in /v1/models is the same number. A request with max_tokens set to 262,145 was rejected with an invalid_request_error.
ByteDance Seed’s release page lists, for Seed2.1 Turbo: 88.0 on BeyondAIME, 67.6 on Terminal Bench 2.1, 80.1 on MMMU-Pro and 82.5 on CharXiv-RQ (both without tools), and 89 on VideoMME. The model card adds 80.3 on MCP-Atlas, a tool-use benchmark. These are ByteDance Seed’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 2 output tokens. high gave the same answer with 51 output tokens, 49 of them reasoning (one run each). The levels in between are minimal, low and medium; above high come xhigh and max.
They are names for the same ByteDance model family. ByteDance Seed calls the family Seed2.1, its announcement says Doubao and Volcano Engine users access it as Doubao Seed 2.1, and BytePlus uses the ID dola-seed-2-1-turbo. On deAPI the model ID is seed-2.1-turbo, and calls are covered by the deAPI Terms of Service.

Send your first Seed 2.1 Turbo request with $5 of free credits

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