DeepSeek has released DeepSeek-V4.1-Flash-1017, a new checkpoint of its V4.1-Flash model, available on its website, app, and API.
Key points
- DeepSeek released V4.1-Flash-1017, an updated AI model.
- The new model claims improved performance and cost efficiency.
- DeepSeek opened its Search and Fetch APIs to developers.
- The model supports a 1 million token context window.
- It achieved a 77.0 score on the DeepSWE benchmark.
The company states this version offers stronger scores, faster task completion, and shorter outputs compared to the September release, describing it as a Pareto improvement in performance and cost.
Alongside the model update, DeepSeek has opened its Search and Fetch APIs to all developers. This provides agent builders with access to a more cost-effective coding model and a first-party web layer accessible through a single API key.
By the numbers
- DeepSWE v1.1 score
- 77.0
- Context window size
- 1M
- Backbone parameters
- 552B
DeepSeek-V4.1-Flash-1017 features a 552 billion backbone parameter count and 196 billion Engram parameters, activating 8 billion parameters per token during prefill and 16 billion during decode. It supports a context window of 1 million tokens with up to 384,000 output tokens.
The model, served as deepseek-flash on the DeepSeek API, reportedly beats the previous V4.1-Flash on all 11 reported benchmarks, with improvements ranging from 2.0 to 11.1 points. Its best score is 77.0 on DeepSWE v1.1, surpassing Claude Opus 5's score of 74.0.
DeepSeek-V4.1-Flash-1017 is an updated post-training checkpoint of DeepSeek-V4.1-Flash, utilizing reinforcement learning with self-feedback for end-to-end project work, including tasks like game creation and 3D modeling. It is tuned for DeepSeek Harness, Tencent CodeBuddy, and WorkBuddy.
Sources and references
Original report
DeepSeek Just Released V4.1-Flash-1017, Scores 77.0 on DeepSWE, Opens Search API
MarkTechPost
Read on MarkTechPost (opens in a new tab)Linked in the original report
- Postx.com/deepseek_ai/status/2111375640717033777 (opens in a new tab)
- Linkapi-docs.deepseek.com/updates (opens in a new tab)
- Linkapi-docs.deepseek.com/guides/search (opens in a new tab)
- Paperarxiv.org/abs/2609.19969 (opens in a new tab)
- Linkdeepseek-harness.github.io/deepseek-harness/en/guide/quickstart (opens in a new tab)
- Modelhuggingface.co/deepseek-ai/DeepSeek-V4.1-Flash (opens in a new tab)
Ref 00A969ZH
Cite this
APA
Interestana AI Editorial. (2026, October 17). DeepSeek Releases V4.1-Flash-1017 Model, Opens Search API. Interestana. https://interestana.com/articles/deepseek-just-released-v41-flash-1017-scores-770-on-deepswe-opens-search-api-00a969zh
MLA
“DeepSeek Releases V4.1-Flash-1017 Model, Opens Search API.” Interestana, 17 Oct. 2026, interestana.com/articles/deepseek-just-released-v41-flash-1017-scores-770-on-deepswe-opens-search-api-00a969zh.
Chicago
Interestana AI Editorial. “DeepSeek Releases V4.1-Flash-1017 Model, Opens Search API.” Interestana, October 17, 2026. https://interestana.com/articles/deepseek-just-released-v41-flash-1017-scores-770-on-deepswe-opens-search-api-00a969zh.
BibTeX
@misc{interestana_00a969zh,
author = {{Interestana AI Editorial}},
title = {{DeepSeek Releases V4.1-Flash-1017 Model, Opens Search API}},
howpublished = {Interestana},
year = {2026},
month = oct,
url = {https://interestana.com/articles/deepseek-just-released-v41-flash-1017-scores-770-on-deepswe-opens-search-api-00a969zh},
note = {Summary of reporting by MarkTechPost, https://www.marktechpost.com/2026/10/17/deepseek-just-released-v4-1-flash-1017-scores-77-0-on-deepswe-opens-search-api/}
}Credit the source
Original reporting: MarkTechPost, “DeepSeek Just Released V4.1-Flash-1017, Scores 77.0 on DeepSWE, Opens Search API”, https://www.marktechpost.com/2026/10/17/deepseek-just-released-v4-1-flash-1017-scores-77-0-on-deepswe-opens-search-api/(opens in a new tab)
Follow this story
Get Artificial Intelligence in your inbox — new stories in 40 words or fewer, once a week.
Subscribe