DeepSeek V4.1 Flash 1017 is now available on AI Gateway, Vercel's unified API for calling models. It is a minor update to DeepSeek V4.1 Flash that improves reasoning, coding, agentic tasks, and image understanding.

The coding gains show up in terminal work and in building and editing whole repositories. The agentic gains appear in multi-step automation. With images, the model reads charts and handles visual reasoning more accurately when it can call tools. It also finishes tasks faster and with shorter outputs than the previous snapshot, so agent runs tend to take less time and use fewer output tokens.

To call the model, use deepseek/deepseek-v4.1-flash-1017 as the model name:

import { streamText } from 'ai'; const result = streamText({ model: 'deepseek/deepseek-v4.1-flash-1017', prompt: 'Write a script that retries failed uploads with exponential backoff.',});

To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run npx vercel ai-gateway setup.

Key Features at a Glance

• Coding: gains in terminal work and in building and editing whole repositories, for developers working on large codebases
• Agentic automation: gains in multi-step tasks, for agent runs that chain several actions
• Image understanding: reads charts and handles visual reasoning more accurately when it can call tools
• Faster runs: finishes tasks faster with shorter outputs than the previous snapshot, which means less time and fewer output tokens per agent run
• Zero Data Retention: supported on AI Gateway for teams with strict data-handling needs
• Budgets and routing: API key budgets and routing rules are built into AI Gateway

Availability

DeepSeek V4.1 Flash 1017 is available on AI Gateway under the model name deepseek/deepseek-v4.1-flash-1017. You can try it in the model playground. AI Gateway reflects provider pricing with no markup and charges no platform fee on inference, including on Bring Your Own Key (BYOK) requests.