Alex Getmanearly AI signals
EN

DeepSeek V4.1 Flash 1017

DeepSeek

Released Updated
Context window
1M
1,048,576 tokens
Input / Output
image, text → text

API pricing

USD / 1M tokens

InputOutputCached input
  • $0.15Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
  • $0.30Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
deepseek-pricing
  • $0.60Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
  • $1.20Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
deepseek-pricing
  • $0.003Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
  • $0.006Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.
deepseek-pricing
Calculate your workload

Timeline

  1. · Weights version · evidence link
Input / output price · USD / 1M tokens
ModelEvidence linksInput / output price
deepseek-flash
standard
deepseek
API route unavailable
$0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) / $0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
deepseek/deepseek-v4.1-flash-1017
standard
openrouter$0.038 / $0.50
deepseek/deepseek-v4.1-flash-1017:batch
batch
openrouter$0.05 / $0.15
deepseek/deepseek-v4.1-flash-1017
standard
vercel-gateway$0.30 / $1.20
  1. · Evidence links · GitHub search · DeepSeek · commits · paperclipai/paperclip · @cryppadotta
  2. · Evidence links · GitHub search · DeepSeek · commits · edtechdev/aied · @edtechdev
    Excerpt
    AI-Model: deepseek/deepseek-v4.1-flash-1017 AI-Role: drafting,revision
  3. · Evidence links · GitHub search · DeepSeek · pulls · vllm-project/vllm · @mgoin
    Excerpt
    `deepseek-ai/DeepSeek-V4.1-Flash-1017` (custom model definition):
  4. · Evidence links · GitHub search · DeepSeek · pulls · sgl-project/sglang · @sghhhh
    Excerpt
    EP4, attention DP4, `flashmla_mega`, no speculative decoding) with `DeepSeek-V4.1-Flash-1017`. The workload starts a decode request (inventory or JSON continuation) on one DP rank and sends
  5. · Evidence links · GitHub search · DeepSeek · pulls · paperclipai/paperclip · @cryppadotta
    Excerpt
    In a chat eval cohort with OpenCode and `openrouter/deepseek/deepseek-v4.1-flash-1017`, the hosts Wafer and DigitalOcean served most model calls. In the case handoff case, `handoff_case` arrived
  6. · Evidence links · GitHub search · DeepSeek · pulls · hakula139/plugins · @hakula139
    Excerpt
    probe with no image `detail` returned HTTP 200, `DeepSeek-V4.1-Flash-1017`, `stop_reason: end_turn`, and a correct image description
  7. · Evidence links · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  8. · Evidence links · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @models-dev-automation[bot]
    Excerpt
    - updated: `/home/runner/_work/models.dev/models.dev/providers/requesty/models/deepseek-v4.1-flash-1017@eu.toml`
  9. · Evidence links · GitHub search · DeepSeek · pulls · agent-of-empires/agent-of-empires · @athal7
    Excerpt
    **AI Model/Tool used:** omp (otari/deepseek/deepseek-v4.1-flash-1017)
  10. · Evidence links · GitHub search · DeepSeek · pulls · Layr-Labs/flock-challenge-multi · @yukon-autoresearch[bot]
    Excerpt
    Model: DeepSeek-V4.1-Flash-1017 Harness: Hermes Agent
  11. · Evidence links · GitHub search · DeepSeek · pulls · ChristianLuciani/profile-as-code · @ChristianLuciani
    Excerpt
    Models: deepseek-flash (deepseek-official) → deepseek-v4.1-flash-1017 (openrouter)

Signals 1

Specifications

DeepSeek V4.1 Flash 1017 is a model from DeepSeek with open weights, released on 17 Oct 2026. The context window is 1,048,576 tokens. Pricing is $0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million input tokens and $0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million output tokens.

Context window
1,048,576
Input
image · text
Output
text
Weights
Open
Input · USD / 1M tokens
$0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
Output · USD / 1M tokens
$0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
Cached input · USD / 1M tokens
$0.003 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.006 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)

Questions

What is the context window of DeepSeek V4.1 Flash 1017?

The context window is 1,048,576 tokens.

How much does DeepSeek V4.1 Flash 1017 cost?

Pricing is $0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million input tokens and $0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million output tokens. Cached input is $0.003 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.006 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million.

Are the weights of DeepSeek V4.1 Flash 1017 publicly available?

Yes. DeepSeek publishes the weights.

When was DeepSeek V4.1 Flash 1017 released?

On 17 Oct 2026.