DeepSeek V4.1 Flash 1017 now available on AI Gateway
By Steven Van ·
The model is available in AI Gateway at provider pricing with no markup, and works in Claude Code, Codex and Cursor after a one-line CLI setup.
DeepSeek V4.1 Flash 1017, a minor update to DeepSeek V4.1 Flash, is now available on Vercel's AI Gateway. The announcement says it improves reasoning, coding, agentic tasks and image understanding.
What improved
- Coding: gains show up in terminal work and in building and editing whole repositories.
- Agentic tasks: gains show up in multi-step automation.
- Images: the model reads charts and handles visual reasoning more accurately when it can call tools.
- Speed: it finishes tasks faster and with shorter outputs than the previous snapshot, so agent runs tend to take less time and use fewer output tokens.
Using it
Set the model name to deepseek/deepseek-v4.1-flash-1017. The example in the release note calls it through the AI SDK's streamText function.
To use it in Claude Code, Codex, Cursor and other tools, install the latest Vercel CLI and run npx vercel ai-gateway setup. The model can also be tried in the model playground.
Pricing and gateway features
AI Gateway reflects provider pricing with no markup. It does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. The gateway also offers usage and cost tracking, retries, failover, custom reporting, Zero Data Retention support, budgets for API keys and routing rules.