AI Agent StoreDeepSeek / Baseten · New hosting option
DeepSeek V4.1 Flash 1017 Fast · Gateway
Run the October 17 Flash model through Baseten on AI Gateway. This option supports long inputs and cached prompts. Test response times on your own workload before paying more for the Fast offer.
First reviewed 2026-10-19 · Checked 2026-11-03. Gateway dates the underlying model October 17. This hosting option was first verified here October 19; it is not another base-model release.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact AI Gateway route ID: deepseek/deepseek-v4.1-flash-1017-fast. Use text and images with tools or structured answers. Baseten markets this option for faster output, but we do not yet have a same-task test showing its response time or total bill.
Thinking settings listed by AI Gateway: none, low, medium, high. These controls apply to this AI Gateway service. We have not confirmed how they match the model maker’s settings, which is the default, or how they perform in comparable independent tests. Verify the exact Gateway catalog entry ↗
Use the full versioned ID to select this offer. Its listed thinking controls differ from the ordinary 1017 OpenRouter offer, which includes max; do not assume the controls produce equivalent results.
Gateway lists 1,048,576 context tokens and 262,144 maximum output tokens. The older unversioned Fast offer lists 32,768 maximum output tokens; it is a separate offer.
Gateway lists $0.60 input, $0.014 cached input and $2.40 output per million tokens. Automatic caching reuses matching prompt prefixes. These are prices for this hosting option; DeepSeek’s direct API uses a different peak/off-peak schedule. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗