DeepSeek / Chat

deepseek-v4.1-flash-1017

A lightweight model for coding, reasoning and everyday questions, using the October 17 update.

POSThttps://orux.top/api/v1/chat/completions

How do the four protocols differ?

These are different interfaces with different request and response formats. Orux currently exposes Chat Completions. The other three client endpoints are not yet available here; provider support does not imply an Orux endpoint is available.

Chat Completions — POST /api/v1/chat/completions · Available on Orux. Send messages; read choices[0].message.content. Streaming uses choices[].delta.
Responses — Not yet available on Orux. Send input and instructions; output[] contains messages or tool calls. Streaming uses events such as response.output_text.delta. It is not an alias for Chat Completions.
Anthropic Messages — Not yet available on Orux. Send messages, a separate system field and required max_tokens. Read content[] blocks; streaming uses message_start/content_block_delta/message_stop.
Gemini GenerateContent — Not yet available on Orux. Send contents[].parts and generationConfig. Read candidates[].content.parts; streaming uses streamGenerateContent.

Format comparison (not callable Orux examples)

These JSON examples explain the formats of unavailable endpoints. Do not send them to Orux. Use the Chat Completions request example on this page.

Authorization

Pass your Orux API key in the request header. Keep keys on your server.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Request body

model: deepseek-v4.1-flash-1017. Place model parameters directly in the request body.

Examples use configured defaults. Replace placeholders in angle brackets with actual values.

Parameters

Fields accepted in the request body for this model.

messagesmessages

Required

Describe your question or task.

max_tokensinteger

Optional

Maximum output tokens; longer answers may cost more.

Range: 1 – 393216Default: 1024

reasoning_effortenum

Optional

Deeper thinking may take longer and cost more.

Values: Direct answer / Brief / Deep / DeepestDefault: high

Advanced

temperaturenumber

Optional

Lower is more predictable, higher more varied. Applies only with thinking off.

Range: 0 – 2

top_pnumber

Optional

Usually leave unchanged: 0.95–1 with thinking; 1 without.

Range: 0.01 – 1

stopstring

Optional

Optional text that ends generation when it appears.

response_formatobject

Optional

Choose plain text for conversation; for JSON, specify the required fields in your message.

Values: Plain text / Structured JSON

toolsobject

Optional

Array of function tools. This page displays calls but does not execute tools.

tool_choiceenum

Optional

Use with tools: auto, none or required.

Values: auto / none / required

thinkingobject

Optional

Use type enabled or disabled; avoid conflicting reasoning_effort settings.

Response examples

Illustrative response structures. Actual content depends on the request.

Open playground