Vercel Adds DeepSeek V4.1 Flash 1017 Ultrafast to AI Gateway
Vercel has added DeepSeek V4.1 Flash 1017 Ultrafast to its AI Gateway through Fireworks, giving developers access to a model that can generate upwards of 1,000 tokens per second. The model is available in public preview and is designed for applications that need to produce output and continue to the next step quickly.
- DeepSeek V4.1 Flash 1017 Ultrafast is available on Vercel AI Gateway through Fireworks.
- The model can generate upwards of 1,000 tokens per second.
- It has a 1M-token context window for large codebases and long inputs.
- The model is in public preview without a waitroom or session time limit.
- AI Gateway has no markup or platform fee on inference, including BYOK requests.
A fast model for coding and agentic workflows
DeepSeek V4.1 Flash 1017 Ultrafast serves the October 17 update of DeepSeek V4.1 Flash through Fireworks' accelerated serverless endpoint. According to Vercel, it is suited to interactive coding, reasoning, and agentic workflows, where reducing the time between one generated result and the next action is important.
The model has a 1M-token context window. That gives applications room to work with large codebases and long inputs, which can be useful for coding tools and other workflows that need to process substantial amounts of context in a single interaction.
How developers can access it
DeepSeek V4.1 Flash 1017 Ultrafast is available on AI Gateway in public preview without a waitroom or session time limit. Developers can select it using the model name deepseek/deepseek-v4.1-flash-1017-ultrafast.
Vercel's example uses the AI SDK's streamText function to send a prompt and stream the result to standard output. The announcement also says the model can be used in Claude Code, Codex, Cursor, and more. To set it up in an agent, developers must install the latest Vercel CLI, run npx vercel ai-gateway setup, and then select the model.
Vercel also directs users to its model playground and coding agents guide for trying and configuring the model.
What AI Gateway adds
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime, according to Vercel. Its features include custom reporting, Zero Data Retention support, budgets for API keys, and routing rules.
Vercel says AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including requests made through Bring Your Own Key, or BYOK. For users building coding tools and agents, the addition combines DeepSeek V4.1 Flash 1017 Ultrafast's high generation speed and large context window with a shared gateway for model access and operational controls.
