DeepSeek V4.1 Flash vs DeepSeek V4.1 Flash 1017
Different efforts: non-thinking · max · Compare all at high
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
DeepSeek V4.1 Flash10.8
DeepSeek V4.1 Flash 101743.3
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
DeepSeek V4.1 Flash5.6
DeepSeek V4.1 Flash 101733.8
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
DeepSeek V4.1 Flash47.8
DeepSeek V4.1 Flash 101766.6
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
DeepSeek V4.1 Flash · max1,440
DeepSeek V4.1 Flash 10171,408
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
DeepSeek V4.1 Flash65.6
DeepSeek V4.1 Flash 101780.6
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Humanity's Last Exam | 10.8 | 43.3 |
| Terminal-Bench 4.0 | 5.6 | 33.8 |
| AutomationBench-AA | 47.8 | 66.6 |
| Arena Text · creative writing | 1,440 · max | 1,408 |
| MMMU-Pro (vision) | 65.6 | 80.6 |
Specs
| Spec | DeepSeek V4.1 Flash | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Input, per 1M | !$0.30 | $0.30 |
| Output, per 1M | !$1.20 | $1.20 |
| Cost per task? | $0.22 | $0.26 |
| Speed, tok/s | 201 | 167 |
| Context | 1M | 1M |
| Weights | Open | Open |
| Released | Sep 2026 | Oct 2026 |
| Memory (4-bit) | — | 458 GB |
| Licence | — | MIT |
| Commercial use | — | Allowed |
| See images | ? | ✓ |
| Read PDFs | ? | — |
| Hear audio | ? | — |
| Watch video | ? | — |
| Call tools | ✓ | ✓ |
| Force a tool call | ? | ✓ |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
DeepSeek V4.1 Flash → DeepSeek V4.1 Flash 1017
Pass back reasoning_content · Chat Completions›
With thinking and tools, return all prior reasoning_content even on turns without tool calls or the API returns HTTP 400.
Disable thinking mode first · Chat Completions›
Required and named tool choices return HTTP 400 in thinking mode; disable thinking first.
Parameters have no effect›
In thinking mode, temperature, presence_penalty and frequency_penalty have no effect.
Values below 0.95›
Flash clamps top_p below 0.95 to 0.95 while thinking and ignores it in non-thinking mode, using 1.0.
Stateless API · Responses›
Responses does not support previous_response_id or conversation; preserve conversation history in your client.
DeepSeek V4.1 Flash 1017 → DeepSeek V4.1 Flash