---
title: "Qwen3.8-Max-Preview Responses API (OpenAI-Compatible)"
method: POST
path: "/v1/responses"
---

# Qwen3.8-Max-Preview Responses API (OpenAI-Compatible)

`POST /v1/responses`

> 🚧 **This model is not yet available, stay tuned**

- Call Qwen3.8-Max-Preview using the OpenAI Responses protocol
- **Flexible input**: `input` can be a string or a Chat-format message array (supporting multimodal `input_text` / `input_image`)
- **Multi-turn conversation**: pass `previous_response_id` to link to the previous response, and the server automatically assembles the context (the response `id` is valid for 7 days)
- **Session caching**: enable by adding `x-dashscope-session-cache: enable` to the request header (default disable); see `usage.input_tokens_details.cached_tokens` for hits
- **Thinking effort**: controlled via `reasoning.effort`
- **Streaming output**: when `stream=true`, returned as Responses events (`response.output_text.delta` / `response.completed`, etc.)

## Headers

- `x-dashscope-session-cache` 'enable' | 'disable'

## Request body

- ResponseRequest
  - `model` 'qwen3.8-max-preview', required — Chat model name
  - `input` union, required — Model input. Can be a string (plain text) or a Chat-format message array (supporting multimodal `input_text` / `input_image`).
    - string
    - InputItem[]
      - `role` 'user' | 'assistant' | 'system' — Message role
      - `content` union — Message content. Pass a string for plain text; pass a content part array for multimodal input.
        - string
        - InputContentPart[]
          - `type` 'input_text' | 'input_image', required — Content type - `input_text`: text - `input_image`: image
          - `text` string — Text content when `type=input_text`
          - `image_url` string — Image URL when `type=input_image`, or a base64 data URL starting with `data:`
  - `instructions` string — Inserted as a system instruction at the start of the context. When using `previous_response_id`, the previous turn's `instructions` are not carried into this turn.
  - `previous_response_id` string — Unique ID of the previous response (the response `id`, valid for 7 days). Used to link multi-turn conversations; the server automatically retrieves and combines that turn's input and output as context.
  - `max_output_tokens` integer — Maximum number of output tokens to generate this time (including thinking).
  - `reasoning` object — Thinking control.
    - `effort` 'low' | 'medium' | 'high' — Thinking effort
  - `store` boolean — Whether to store this response. - `true` (default): can be referenced by `previous_response_id` - `false`: not stored and cannot be referenced later
  - `stream` boolean — Whether to return a Responses event stream.
  - `temperature` number — Sampling temperature, range `[0, 2]`.
  - `top_p` number — Nucleus sampling parameter, range `(0, 1]`.
  - `tools` Tool[] — List of tools. Supports built-in tools (`web_search` for web search, `web_extractor` for web extraction, `code_interpreter` for code interpretation) and custom `function` tools.
    - `type` 'web_search' | 'web_extractor' | 'code_interpreter' | 'function', required — Tool type
    - `name` string — Function name when `type=function`
    - `parameters` object — Parameter JSON Schema when `type=function`

## Response `200`

Generated successfully

- ResponseObject
  - `id` string — Unique ID of this response (valid for 7 days, can be used as `previous_response_id`)
  - `object` string
  - `status` string — Response status
  - `model` string
  - `output` object[] — Array of output items (including `message` / `reasoning` / built-in tool calls, etc.)
  - `usage` Usage — Usage and billing information
    - `billing_rule` 'per_call' | 'per_token' | 'per_second' — Billing rule
    - `credits_reserved` number — Estimated credits to be consumed
    - `user_group` 'default' | 'vip' — User group category

## Other responses

- `400` — Invalid request parameters
- `401` — Unauthenticated, invalid or expired token
- `402` — Insufficient balance
- `429` — Too many requests (rate limited)
- `500` — Internal server error

---

[API](https://skmtc.dev/evolink/apis/get-credits-usage-api.md) · [All operations](https://skmtc.dev/evolink/apis/get-credits-usage-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/evolink/get-credits-usage-api/revisions/88edb0ec881f/schema)