Summarize with AI
DeepSeek has released DeepSeek-V4.1-Flash-1017, an update to V4.1-Flash. DeepSeek says it scores higher, finishes tasks faster and writes shorter answers, which makes it cheaper to run. The weights are open under the MIT license, and DeepSeek says the model is on its website, in its app and in the API.
DeepSeek also opened two new APIs, Search and Fetch, built on its own search engine. All numbers below are DeepSeek's own, and the test setups differ from benchmark to benchmark.
What it is
- A minor update to DeepSeek-V4.1-Flash.
- 763B parameters, 1M-token context.
- MIT license for the code and the weights, on Hugging Face.
- Shorter outputs and shorter task times than the previous Flash, according to DeepSeek.
Benchmarks: new Flash vs. previous Flash
| Benchmark | V4.1-Flash-1017 | V4.1-Flash |
|---|---|---|
| Terminal-Bench 4.0 | 42.3 | 31.2 |
| ProgramBench | 29.1 | 20.3 |
| DeepSWE v1.1 | 77.0 | 74.2 |
| Automation-Bench v1.0.6 | 60.5 | 54.8 |
| Agents' Last Exam | 35.4 | 31.8 |
| HLE (no tools) | 42.6 | 36.8 |
Benchmarks: against Claude Opus 5 and GPT 5.6-Sol
| Benchmark | V4.1-Flash-1017 | Claude Opus 5 | GPT 5.6-Sol |
|---|---|---|---|
| DeepSWE v1.1 | 77.0 | 74.0 | 73.0 |
| Automation-Bench v1.0.6 | 60.5 | 50.3 | 45.8 |
| Agents' Last Exam | 35.4 | 28.6 | 26.7 |
| HLE (no tools) | 42.6 | 56.3 | 44.5 |
| Terminal-Bench 4.0 | 42.3 | 51.8 | 39.9 |
| ProgramBench | 29.1 | 37.0 | 23.0 |
| NL2Repo-Bench | 68.2 | 75.3 | 56.8 |
DeepSeek notes that Terminal-Bench 4.0 was run in the Claude Code framework and DeepSWE in Mini-SWE-V2.
Price: Search and Fetch APIs
| API | What it does | Price |
|---|---|---|
| Search | Finds web pages for a query, returns structured results | $0.75 per 1,000 successful requests |
| Fetch | Gets one web page and returns it as Markdown | $0.75 per 1,000 successful requests |
- Failed requests, empty search results and timeouts are not billed.
- Calls made through DeepSeek Harness, Claude Code or Codex are free until billing starts at 00:00 Beijing time on November 1, 2026.
- Limit: 5 requests per second for each API, per account.
Sources
Did this land? Leave a reaction.
Discussion
0 commentsMembers can join the discussion
Become a member to comment and reply to other members.
Become a MemberNo comments yet
Be the first to start the discussion.