DeepSeek V4.1 Flash 1017 API pricing and integration guide

Current prices and model reference

Model ID

deepseek-v4.1-flash

Documented context

1M

Documented image input

Supported

Live model multiplier

Expression billing

Input price

—

Output price

—

Prices are in CNY. A 1× multiplier equals CNY 0.4 per million input tokens. Output and cache charges follow the billing configuration; your usage record is authoritative.

When to consider this model

Consider this route for workflows combining Chinese documents, code and screenshots. The gateway reference lists 1M context and multimodal input; compare output quality, latency and recorded cost on your own tasks.

How to evaluate it

Validate a short text request first, then add one screenshot with a specific question. Increase document length gradually and keep a text-only control to check whether visual details were understood.

What to check before integration

1017 identifies the release, not a new API ID. This gateway retains deepseek-v4.1-flash; direct DeepSeek calls use deepseek-flash. Contact support for pinned upstream-version requirements rather than relying on the display name.

Client configuration

In a client supporting a custom API endpoint, enter this base URL and model ID with your own API key. Select the protocol described in the client tutorial and validate a short request first.

Base URL: https://api.llm-token.cn/v1
Model ID: deepseek-v4.1-flash