Use Seed 2.0 Lite 260228 with Comfy Router

API Reference for byteplus/seed-2-0-lite-260228, served by Comfy Router from BytePlus.

Quick start

Create a key in your Comfy workspace and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP. Model ID: byteplus/seed-2-0-lite-260228 Endpoint: POST https://api.comfy.org/v2/models/byteplus/seed-2-0-lite-260228

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment.
# The SDK automatically creates an idempotency key and reuses it for automatic retries.
with Comfy() as client:
    result = client.models.run(
        "byteplus/seed-2-0-lite-260228",
        {
            "input": "Reply with the single word: ok",
        },
    )

print(result)

import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment.
// The SDK automatically creates an idempotency key and reuses it for automatic retries.
const { data } = await comfy.models.run("byteplus/seed-2-0-lite-260228", {
  input: "Reply with the single word: ok",
});

console.log(data);

curl https://api.comfy.org/v2/models/byteplus/seed-2-0-lite-260228 \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d "{\"input\": \"Reply with the single word: ok\"}"

Schema

Input

object

Context-cache configuration.

boolean

default:"false"

When true, only create the public prefix cache; the model does not respond.

string

Possible values: enabled, disabled

object

Context-management strategies (clear_thinking, clear_tool_uses) applied to keep the context window manageable.

object[]

A single context-edit strategy, discriminated by type.

integer

Unix timestamp (seconds, UTC) at which the stored response and cache expire. Range (creation_time, creation_time + 604800]. Default: creation_time + 259200 (3 days).

string[]

Additional output fields to include. Currently supported: reasoning.encrypted_content (encrypted+compressed reasoning for manual multi-turn reuse).

string | object[]

required

Text content or list of input items provided to the model.

string

System/developer message prepended as the first instruction. Not compatible with caching — if caching.type is enabled, setting instructions returns an error.

integer

Maximum output tokens (response + chain-of-thought).

integer

Range: 1 to 10

string

Model ID or Endpoint ID. See https://docs.byteplus.com/en/docs/ModelArk/1330310 for the model list and https://docs.byteplus.com/en/docs/ModelArk/1099522 for Endpoint IDs. A direct v1 call to POST /proxy/byteplus/api/v3/responses MUST supply it — the proxy refuses any value outside its own allowlist, and an omitted one, with a 400. It is NOT in the Comfy Router input schemas’ required lists because Router fills it from the {model} path segment of /v2/models/byteplus/{model}, so a Router caller omits it.

string

ID of the previous response, used to continue a multi-turn conversation. Insert ~100ms between requests to avoid failures.

object

Limits the workload of deep thinking.

string

minimal disables thinking entirely. With thinking.type = disabled, only minimal is allowed.Possible values: minimal, low, medium, high

boolean

default:"true"

When true, the response is persisted and retrievable by ID for multi-turn use.

number

default:"1"

Range: 0 to 2Format: float

object

Output-format configuration.

object

Text-output format discriminated by type. text returns natural language, json_object returns a free-form JSON object, json_schema constrains output to a caller-supplied JSON Schema.

object

Controls deep-thinking mode.

string

enabled: always reason before responding. disabled: respond without additional reasoning. auto: model decides per-query.Possible values: enabled, disabled, auto

`none`, `auto`, `required` | object

Tool-selection mode. Only seed-1-6 models support this field.

object[]

A tool the model may invoke. Currently only function is supported.

string

required

object

required

JSON Schema describing the function’s parameters.

string

default:"\"function\""

required

Possible values: function

number

default:"0.7"

Range: 0 to 1Format: float

Generated from the schema Router serves at GET /v2/models/byteplus/seed-2-0-lite-260228/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

object

boolean

string

Possible values: enabled, disabled

object

Context-management strategies that were actually applied during this response. Unlike the request-side BytePlusResponseContextManagement (which configures strategies), this echoes the strategies the server invoked, with counts of what was cleared.

object[]

One applied context-edit, discriminated by type.

integer

required

Unix timestamp (seconds) when the response was created.

object

Error details. Null when the response succeeded.

string

required

string

required

integer

Unix timestamp (seconds) when the stored response expires.

string

required

Unique ID of the response. Use as previous_response_id to continue the conversation.

object

Populated when status is incomplete.

string

e.g. max_output_tokens, content_filter.

string

Echo of the request’s instructions field.

integer

object

string

required

Model ID that generated the response.

string

default:"\"response\""

required

Possible values: response

object[]

required

Ordered output items produced by the model.

string

object

string

Possible values: minimal, low, medium, high

string

TPM-guarantee-package usage. default means none.Possible values: default

string

required

Possible values: in_progress, completed, incomplete, failed, cancelled

boolean

number

Format: float

object

Echo of the request’s text field.

object

Text-output format discriminated by type. text returns natural language, json_object returns a free-form JSON object, json_schema constrains output to a caller-supplied JSON Schema.

object

string

Possible values: enabled, disabled, auto

`none`, `auto`, `required` | object

object[]

A tool the model may invoke. Currently only function is supported.

string

required

object

required

JSON Schema describing the function’s parameters.

string

default:"\"function\""

required

Possible values: function

number

Format: float

object

Token-usage breakdown for billing and observability.

integer

required

Total tokens in the request.

object

Breakdown of input tokens (cache hits, etc).

integer

Tokens served from the context cache.

integer

required

Total tokens generated by the model.

object

Breakdown of output tokens (reasoning, etc).

integer

Tokens consumed by chain-of-thought.

object

Per-tool invocation counts.

integer

Number of image-processing tool calls.

integer

Number of MCP tool calls.

integer

Number of web-search tool invocations.

object

Per-tool breakdown of sub-tool invocation counts.

object

e.g. {"zoom":1,"point":1,"grounding":1}.

object

e.g. {"mcp_server_tos":1,"mcp_server_tls":1}.

object

e.g. {"toutiao":1,"moji":1,"search_engine":1}.

integer

required

input_tokens + output_tokens.

Examples

Input

{
  "input": "Reply with the single word: ok"
}

Output

{
  "created_at": 1767225600,
  "id": "resp_0a1b2c3d4e5f6a7b8c9d0e1f",
  "model": "seed-2-0-lite-260228",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "text": "ok",
          "type": "output_text"
        }
      ],
      "id": "msg_0a1b2c3d4e5f6a7b8c9d0e1f",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed",
  "usage": {
    "input_tokens": 14,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 2,
    "total_tokens": 16
  }
}

Before you ship

The SDKs create an Idempotency-Key and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes. When a request fails, Router sends an X-Comfy-Error-Type response header explaining why. A 422 means Router rejected the input before calling the provider. Download generated assets promptly because result URLs can expire.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Using the Router API

Model discovery, validation errors, retries, and billing.

Limitations

What Router does not do today, and what to use instead.

Develop with Comfy

Deploy ComfyUI

Run Workflows

Comfy Router

Comfy CLI

Specifications

Use Seed 2.0 Lite 260228 with Comfy Router

Quick start

Schema

Input

Output

Examples

Input

Output

Before you ship

Headers

Using the Router API

Limitations

​Quick start

​Schema

​Input

​Output

​Examples

​Input

​Output

​Before you ship

Headers

Using the Router API

Limitations

Quick start

Schema

Input

Output

Examples

Input

Output

Before you ship