Skip to content
HIPS
  • Earn with your GPU
  • Pricing
  • Docs
Sign inJoin early access
01Model page_

DeepSeek: DeepSeek V4.1 Flash 1017

In early accessdeepseek-v4.1-flash-1017

Alias deepseek-v4.1-flash-1017 > deepseek-v4.1-flash-1017-1

DeepSeek V4.1 Flash 1017 is the October 2026 update of DeepSeek V4.1 Flash, a sparse mixture-of-experts model from DeepSeek with 552B total parameters (8B active per input token), Engram conditional memory, and a 1M-token context window. It improves reasoning, coding, and agentic performance over the September release while reducing output length and task execution time. It is suited for coding, agent workflows, and high-volume tool use, with a controllable reasoning effort.Reasoning is supporte

Join early accessExplore models

We are inviting early-access interest while we develop the platform.

02The model's fields_
03Versions and aliases_
Versions of DeepSeek: DeepSeek V4.1 Flash 1017
Model versionStatusReleasedRetiresHugging Face revision
deepseek-v4.1-flash-1017-1CURRENTLiveNov 16, 2026
  • deepseek-v4.1-flash-1017>points atdeepseek-v4.1-flash-1017-1From Nov 16, 2026
04Rates, per pool_

Rates

Certified pool

Per million tokens

On demand

Input
$0.098From Nov 16, 2026
Cached input
Billed as input
Output
$0.70From Nov 16, 2026

Batch

Batch is not offered for this model.

DeepSeek: DeepSeek V4.1 Flash 1017, Certified pool
InputCached inputOutput
On demand$0.098From Nov 16, 2026Billed as input$0.70From Nov 16, 2026
BatchBatch is not offered for this model.

In every pool, every input token is billed at the input rate today.

DeepSeek: DeepSeek V4.1 Flash 1017

Input per million tokens

$0.098

Unchanged since November 16, 2026

  • November 16, 2026: $0.098

Output per million tokens

$0.70

Unchanged since November 16, 2026

  • November 16, 2026: $0.70

Product

  • Inference
  • Models
  • Deploy your model
  • Always-on GPU capacity
  • How it works
  • Use cases
  • Pricing

Developer

  • Docs
  • Quickstart
  • Migrate to HIPS
  • HIPS SDK
  • Batch jobs
  • API reference

Provider

  • Earn with your GPU
  • Register GPU interest
  • Download for Mac
  • Download for Windows
  • Download for Linux

Resource

  • Security and Data
  • Resources
  • llms.txt

Compare

  • OpenRouter alternatives
  • Together AI alternatives
  • Groq alternatives
  • All comparisons

Company

  • About
  • Contact
  • Affiliate program
  • HIPS Payments

Legal

  • Legal
  • Consumer Health Data Privacy Policy
  • Report content
  • Cookie preferences

Support

  • Contact HIPS
  • Looking for payments support?

HIPS. AI inference for builders.

hips.com

Hyperscale Inference Processing Systems OÜ