DeepSeek V4.1 Flash 1017 Ultrafast comes to Vercel AI Gateway
Vercel added DeepSeek V4.1 Flash 1017 Ultrafast to AI Gateway, served through Fireworks' accelerated serverless endpoint. It is available in public preview with no waitlist and no session time limit, under the model name deepseek/deepseek-v4.1-flash-1017-ultrafast, callable through AI SDK or Chat Completions. Developers can also select it inside Claude Code, Codex, Cursor and similar agents after installing the latest Vercel CLI and running setup. Vercel says AI Gateway matches provider pricing with no markup and no platform fee on inference, including bring-your-own-key requests.
Why it matters
Developers get a high-throughput model option alongside other models in one gateway, which suits agent and coding loops that need fast turnaround, and Vercel says it adds no markup or platform fee on top of provider pricing.
Sources
- PrimaryVercel
Written by AIToolMaps from the source above and checked against it sentence by sentence.