DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a DeepSeek model that accepts text and image input and returns text. It offers a 1,048,576-token context window with up to 393,216 completion tokens, so long documents, large codebases, or extended conversations can fit in a single request. It supports tool calling and reasoning; structured output support is not listed, so verify it before building pipelines that depend on strict schemas. Open-weights status is also unspecified. At $0.15 per million input tokens and $0.60 per million output tokens, this model belongs on the shortlist for teams running high-volume or long-context workloads where cost per token matters more than peak capability. Its blended benchmark score of 66.3 comes from a single independent benchmark (AI Index score of 65.1), which is thin evidence. Treat its standing as provisional and test it on your own tasks before committing.
Benchmark results
Independent, published benchmarks. Blended score 66.3 across 1 benchmark, last refreshed 2026-10-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 65.1 |
- Model ID
- deepseek/deepseek-v4.1-flash
- Vendor
- deepseek
- Released
- September 2026
- Tokenizer
- DeepSeek
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 393,216 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.15/M input and $0.60/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.10 |
| A month of a busy support chatbot | 5M in / 2M out | $1.95 |
Price & spec history
Tracked daily by PicksByModel since 2026-09-11.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-10-13 | $0.15 | $0.60 | 1,048,576 |
| 2026-10-07 | $0.30 | $1.20 | 1,048,576 |
| 2026-10-04 | $0.00 | $2.40 | 1,048,576 |
| 2026-10-03 | $0.30 | $1.20 | 1,048,576 |
| 2026-10-02 | $0.03 | $0.75 | 1,048,576 |
| 2026-10-01 | $0.02 | $0.40 | 1,048,576 |
| 2026-09-29 | $0.30 | $1.20 | 1,048,576 |
| 2026-09-27 | $0.04 | $0.29 | 1,048,576 |
| 2026-09-26 | $0.14 | $0.42 | 1,048,576 |
| 2026-09-25 | $0.15 | $0.60 | 1,048,576 |
| 2026-09-24 | $0.14 | $0.42 | 1,048,576 |
| 2026-09-11 | $0.15 | $0.60 | 1,048,576 |
Category rankings
Where DeepSeek: DeepSeek V4.1 Flash places across the 11 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #7 | Image CaptioningVision · of 25 ranked | 121 |
| #12 | Short-Form SummarizationWriting · of 25 ranked | 127 |
| #12 | Email DraftingWriting · of 25 ranked | 123 |
| #12 | Language LearningEducation · of 25 ranked | 123 |
| #12 | Chat CompanionPersonal · of 25 ranked | 127 |
| #12 | Trivia & General KnowledgePersonal · of 25 ranked | 117 |
| #15 | Code CompletionCode · of 25 ranked | 133 |
| #20 | Sales / Cold EmailBusiness · of 25 ranked | 119 |
| #20 | Job Application DraftingBusiness · of 25 ranked | 119 |
| #20 | Journaling HelperPersonal · of 25 ranked | 119 |
| #20 | Recipe GenerationPersonal · of 25 ranked | 119 |
Similar models
DeepSeek: DeepSeek V4.1 Flash (batch)
DeepSeek: DeepSeek V4 Flash Vision Exp
DeepSeek: DeepSeek V4 Flash 0731
DeepSeek: DeepSeek V4 Flash 0423
DeepSeek: DeepSeek V4 Pro 0813
DeepSeek: DeepSeek V4 Pro 0423
Quick answers
- How much does DeepSeek: DeepSeek V4.1 Flash cost?
- $0.15 per million input tokens and $0.60 per million output tokens.
- What is DeepSeek: DeepSeek V4.1 Flash's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does DeepSeek: DeepSeek V4.1 Flash support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can DeepSeek: DeepSeek V4.1 Flash process images?
- Yes, it accepts image input.