curl --request POST \
  --url https://direct.evolink.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "deepseek-v4-flash",
  "input": "Introduce Hangzhou in one sentence."
}
'

{
  "id": "resp_9f2c1a4b8e7d",
  "object": "response",
  "created_at": 1755000000,
  "status": "completed",
  "model": "deepseek-v4-flash",
  "output": [
    {
      "id": "rs_2b7f",
      "type": "reasoning",
      "summary": [],
      "content": [
        {
          "type": "reasoning_text",
          "text": "The user wants a one-sentence introduction covering both geography and culture."
        }
      ]
    },
    {
      "id": "msg_5d1a",
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hangzhou is the capital of Zhejiang Province, known for West Lake and its digital economy.",
          "annotations": []
        }
      ]
    }
  ],
  "error": null,
  "incomplete_details": null,
  "usage": {
    "input_tokens": 694,
    "input_tokens_details": {
      "cached_tokens": 640
    },
    "output_tokens": 20,
    "output_tokens_details": {
      "reasoning_tokens": 10
    },
    "total_tokens": 714
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid authentication credentials",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": 403,
    "message": "Model access denied",
    "type": "permission_error"
  }
}

{
  "error": {
    "code": 404,
    "message": "Model not found",
    "type": "not_found_error"
  }
}

{
  "error": {
    "code": 413,
    "message": "Request entity too large",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "server_error"
  }
}

{
  "error": {
    "code": 502,
    "message": "Bad gateway",
    "type": "server_error"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "server_error"
  }
}

Responses API

DeepSeek V4 - Responses API

Call DeepSeek V4 models using the OpenAI Responses protocol
Supported models: deepseek-v4.1-flash-1017 / deepseek-v4.1-flash / deepseek-v4-flash / deepseek-v4-pro / deepseek-v4-flash-vision-exp
Input shapes: input can be plain text or an array of input items (message, function call, function result, reasoning, search record)
Image understanding: deepseek-v4.1-flash / deepseek-v4.1-flash-1017 / deepseek-v4-flash-vision-exp accepts input_image content blocks inside content and supports multiple images
System instructions: provided via instructions, equivalent to a leading system message
Thinking mode: controlled by reasoning.effort; thinking content is returned as a reasoning output item
Streaming: semantic SSE events ending with response.completed; no [DONE] is sent
Tool calling: supports Function Calling; the built-in web_search tool is not supported
Structured output: enabled via text.format for JSON object or JSON Schema
Context caching: requests sharing a prefix hit the cache automatically, greatly reducing input cost

Streaming events: response.created, response.output_item.added, response.reasoning_text.delta, response.output_text.delta, with terminal events response.completed / response.incomplete / response.failed. Every event carries a sequence_number for ordering.

Fields with no effect: the following OpenAI fields can be sent without error, but produce no actual effect.

Field	Behavior
`store`	Always `false`; responses are not stored
`previous_response_id`	Always `null`; resuming a conversation is not supported
`conversation`	Not supported
`background` / `metadata` / `include`	Ignored
`prompt` / `truncation` / `service_tier`	Ignored
`safety_identifier` / `context_management`	Ignored
`stream_options`	Ignored
`prompt_cache_key` / `prompt_cache_retention`	Ignored
`parallel_tool_calls`	Ignored; parallel tool calls are always enabled
`max_tool_calls`	Ignored
`file_search` / `code_interpreter` / `mcp` tools	Ignored

Other limitations:

Custom tools (type: custom) support apply_patch only
Passing the web_search tool does not raise an error, but no search is performed
Images via input_image are supported only by deepseek-v4.1-flash / deepseek-v4.1-flash-1017 / deepseek-v4-flash-vision-exp, and PDF files via input_file only by deepseek-v4.1-flash / deepseek-v4-flash-vision-exp; deepseek-v4-flash / deepseek-v4-pro cannot read this content and may replace it with placeholders; deepseek-v4.1-flash-1017 accepts a PDF without error but cannot read its content. See input_file below for the PDF Base64 format.
Images may appear only in messages with role: user; placing one in system or assistant returns HTTP 400
Input exceeding the context window returns 400 directly, with no automatic truncation

POST

responses

curl --request POST \
  --url https://direct.evolink.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "deepseek-v4-flash",
  "input": "Introduce Hangzhou in one sentence."
}
'

{
  "id": "resp_9f2c1a4b8e7d",
  "object": "response",
  "created_at": 1755000000,
  "status": "completed",
  "model": "deepseek-v4-flash",
  "output": [
    {
      "id": "rs_2b7f",
      "type": "reasoning",
      "summary": [],
      "content": [
        {
          "type": "reasoning_text",
          "text": "The user wants a one-sentence introduction covering both geography and culture."
        }
      ]
    },
    {
      "id": "msg_5d1a",
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hangzhou is the capital of Zhejiang Province, known for West Lake and its digital economy.",
          "annotations": []
        }
      ]
    }
  ],
  "error": null,
  "incomplete_details": null,
  "usage": {
    "input_tokens": 694,
    "input_tokens_details": {
      "cached_tokens": 640
    },
    "output_tokens": 20,
    "output_tokens_details": {
      "reasoning_tokens": 10
    },
    "total_tokens": 714
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid authentication credentials",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": 403,
    "message": "Model access denied",
    "type": "permission_error"
  }
}

{
  "error": {
    "code": 404,
    "message": "Model not found",
    "type": "not_found_error"
  }
}

{
  "error": {
    "code": 413,
    "message": "Request entity too large",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "server_error"
  }
}

{
  "error": {
    "code": 502,
    "message": "Bad gateway",
    "type": "server_error"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "server_error"
  }
}

BaseURL: The default BaseURL is https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit the API Key Management Page to obtain your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:deepseek-v4-flash

required

Model ID

deepseek-v4.1-flash-1017: DeepSeek V4.1 Flash 1017 (latest version), with text and native image understanding, 1M context and up to 384K output tokens; more concise responses and lower latency than the previous version
deepseek-v4.1-flash: Previous version of DeepSeek V4.1 Flash, with the capabilities listed above; use deepseek-v4.1-flash-1017 for the latest version
deepseek-v4-flash: fast and general-purpose, suited to everyday chat, summarization and extraction
deepseek-v4-pro: deep reasoning, suited to complex math, code and multi-step planning
deepseek-v4-flash-vision-exp: Legacy model name, now routed to DeepSeek V4.1 Flash; use deepseek-v4.1-flash for new integrations

Image understanding requires deepseek-v4.1-flash / deepseek-v4.1-flash-1017 / deepseek-v4-flash-vision-exp: The other two models do not raise an error for input_image, but replace it with placeholder text and discard the actual image. The request is still billed.

Available options:

deepseek-v4-flash,

deepseek-v4-pro,

deepseek-v4-flash-vision-exp,

deepseek-v4.1-flash,

deepseek-v4.1-flash-1017

Example:

"deepseek-v4-flash"

input

Model input. At least one of input and instructions must be provided.

String form: the whole text is treated as a single user message
Array form: a list of input items supporting five types — message, function_call, function_call_output, reasoning, web_search_call

Image input: With deepseek-v4.1-flash / deepseek-v4.1-flash-1017 / deepseek-v4-flash-vision-exp, a message item may mix input_text and input_image blocks in its content array.

Multi-turn conversations: the endpoint is stateless, so continuing a conversation requires putting the full history into the array.

Example:

"Introduce Hangzhou in one sentence."

instructions

string

System-level instructions, equivalent to a system message inserted at the very front; used to set the role, tone and output constraints.

Example:

"You are a meticulous technical writer. Keep answers concise."

stream

boolean

default:false

Whether to stream the response

false (default): returns the complete response object at once
true: pushes semantic SSE events; the final event is response.completed / response.incomplete / response.failed, and no [DONE] is sent

Example:

false

max_output_tokens

integer

Maximum number of output tokens for this generation (including thinking tokens). Range 1 to 393216 (384K); deepseek-v4.1-flash-1017 returns HTTP 400 for values outside this range. Leave empty to let the model decide.

Required range: 1 <= x <= 393216

Example:

4096

temperature

number

default:1

Sampling temperature; higher values make output more random. Has no effect in thinking mode.

Required range: 0 <= x <= 2

Example:

1

top_p

number

default:1

Nucleus sampling threshold. Adjust either this or temperature, not both. Has no effect in thinking mode.

Required range: x <= 1

Example:

1

top_logprobs

integer

Return the most likely candidate tokens and their log probabilities at each position.

Required range: 0 <= x <= 20

Example:

0

reasoning

object

Thinking mode configuration. DeepSeek V4 enables thinking by default; thinking content is returned as a reasoning output item, and its tokens count toward output and are billed at the output rate.

Show child attributes

text

object

Text output format configuration.

Show child attributes

tools

Tool definition · object[]

List of tools available to the model. Function tools are executed by the client, which returns the result as function_call_output. The built-in web_search tool is not supported: passing it does not raise an error, but no search is performed.

Show child attributes

tool_choice

Tool choice strategy

none: tool calling disabled
auto (default): the model decides
required: at least one tool must be called
{"type": "function", "name": "get_weather"}: force a specific function

Example:

"auto"

Response

Generation successful

Response object of the Responses endpoint.

string

Unique identifier of this response

Example:

"resp_9f2c1a4b8e7d"

object

string

Object type, always response

Example:

"response"

created_at

integer

Creation time as a Unix timestamp (seconds)

Example:

1755000000

status

enum<string>

Response status

completed: finished normally
in_progress: still generating
incomplete: truncated, e.g. by length; see incomplete_details
failed: generation failed; see error

Available options:

in_progress,

completed,

incomplete,

failed

Example:

"completed"

model

string

ID of the model that actually generated this response

Example:

"deepseek-v4-flash"

output

object[]

List of output items in generation order. Fields per type:

reasoning: the thinking process, with id, status, content (list of reasoning_text blocks) and summary
message: the final answer, with id, status, role and content (list of output_text blocks)
function_call: a function call from the model, with id, status, call_id, name and arguments; the client executes it and returns the result as function_call_output

error

object | null

Failure reason; null on success

incomplete_details

object | null

Truncation reason; null when not truncated

usage

object

Token usage statistics (including cache and reasoning breakdowns)

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

DeepSeek V4 - Responses API

Authorizations

Body

Response