Skip to main content
POST
Chat completion with Seed 2.1 Turbo
Use the Playground on the right: put Bearer sk-your-api-key in Authorization. The default example has deep thinking disabled (thinking.disabled) so you get a fast response on the first send.
The model has deep thinking ON by default — even simple questions produce hundreds of reasoning tokens first. Keep "thinking": {"type": "disabled"} from the example while debugging; switch to reasoning_effort (low / medium / high) when you actually need reasoning. Capabilities, pricing, and caching are covered in the Seed 2.1 Turbo Overview.
  • With thinking on, give max_tokens headroom (reasoning counts against the output budget) — 3000+ recommended
  • A misspelled model name returns 503 (no available channel), not 404

Parameter Quick Reference

Response Highlights

  • With thinking on, choices[0].message carries reasoning_content (full reasoning text) besides content
  • Thinking spend: usage.completion_tokens_details.reasoning_tokens
  • Implicit cache hits: usage.prompt_tokens_details.cached_tokens (a repeated long prefix hits from the 2nd request)

Authorizations

Authorization
string
header
required

API Key from the APIYI console

Body

application/json
model
enum<string>
default:dola-seed-2-1-turbo-260628
required

Model ID, fixed to dola-seed-2-1-turbo-260628

Available options:
dola-seed-2-1-turbo-260628
messages
object[]
required

Conversation messages, standard OpenAI format

max_tokens
integer
default:500

Max output tokens. Reasoning counts against this too - give it headroom (e.g. 2000+) when thinking is on

thinking
object

Deep-thinking switch. ON by default; pass {"type": "disabled"} to turn it off and cut latency and output tokens sharply

reasoning_effort
enum<string>

Thinking depth tier (do not combine with thinking.disabled). Measured: low ~226, high ~960 reasoning tokens

Available options:
low,
medium,
high
stream
boolean
default:false

Stream via SSE. Combine with stream_options.include_usage to get usage in the final chunk

temperature
number

Sampling temperature

response_format
object

Structured output. Supports {"type": "json_schema", "json_schema": {name, strict, schema}}

tools
object[]

Function-calling tool list, standard OpenAI format

Response

Chat completion succeeded

id
string

Request ID

model
string
choices
object[]

Completion results. Besides content, message carries reasoning_content when thinking is on

usage
object

Usage. completion_tokens_details.reasoning_tokens = thinking spend; prompt_tokens_details.cached_tokens = implicit cache hits