# DeepSeek V4.1 Flash

> DeepSeek's smaller V4.1 model: 552B parameters, 8B active on input and 16B on output, a 1M context, vision in and text out. Open weights.

- Date: 2026-09-29
- HTML: https://anyrouter.dev/blog/releases/deepseek

## Models

- `deepseek/deepseek-v4.1-flash` (DeepSeek V4.1 Flash) — 552B MoE, 1M context, vision in, text out. MIT weights.

## Notes

[`deepseek/deepseek-v4.1-flash`](https://anyrouter.dev/model/deepseek/deepseek-v4.1-flash) is DeepSeek V4.1 Flash, the smaller model in the V4.1 family. DeepSeek describes a 552B-parameter mixture of experts with a causal encoder-decoder: 8B parameters active while it reads, 16B while it writes. It takes text and images, answers in text, and the context window is 1,048,576 tokens. Reasoning effort is controllable. The weights are on [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash) under MIT. The [release note](https://api-docs.deepseek.com/news/news260910) and the [tech report](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeek_V41_Tech_Report.pdf) are DeepSeek's.

DeepSeek's own agentic chart puts V4.1 Flash at 30.0 on Terminal-Bench 3.0, 74.2 on DeepSWE v1.1, 88.1 on CyberGym, and 54.8 on Automation-Bench. Those bars are the vendor's comparison with Kimi-K3, GLM-5.3, Opus 5, and GPT-5.6 Sol.

![Bar chart of DeepSeek V4.1 Flash against Kimi-K3, GLM-5.3, Opus 5 and GPT-5.6 Sol on Terminal-Bench 3.0, DeepSWE v1.1, CyberGym and Automation-Bench. DeepSeek published the chart.](https://anyrouter.dev/img/models/deepseek/deepseek-v4.1-flash/benchmark-1.webp)

_Agentic scores from DeepSeek's V4.1 Flash model card._

Epoch AI scores in our catalog, separate from that chart: GPQA Diamond 89.8, OTIS Mock AIME 98.3, ARC-AGI-2 72.9, SciCode 51.9, SimpleQA Verified 42.9.

| Benchmark | Score | Source |
| --- | --- | --- |
| Terminal-Bench 3.0 | 30.0 | DeepSeek |
| DeepSWE v1.1 | 74.2 | DeepSeek |
| CyberGym | 88.1 | DeepSeek |
| Automation-Bench | 54.8 | DeepSeek |
| GPQA Diamond | 89.8 | Epoch AI |
| OTIS Mock AIME | 98.3 | Epoch AI |
| ARC-AGI-2 | 72.9 | Epoch AI |
| SciCode | 51.9 | Epoch AI |
| SimpleQA Verified | 42.9 | Epoch AI |

The same card shows the KV cache shrinking across DeepSeek generations. DeepSeek says V4.1 Flash needs about a quarter of the previous generation's HBM for that cache, and about an eighth of the SSD. Cache-hit cost is a large share of a long agent run, so a smaller cache is the point of the architecture.

![Bar chart of global KV cache bytes per token for DeepSeek V1, V3.2, V4-Flash and V4.1-Flash. Each generation is smaller.](https://anyrouter.dev/img/models/deepseek/deepseek-v4.1-flash/comparison-1.webp)

_KV cache bytes per token, from DeepSeek's model card._

- App code: [Vercel AI SDK](https://anyrouter.dev/use-cases/ai-sdk) or [OpenAI SDK](https://anyrouter.dev/use-cases/openai-sdk).
- Coding agent: `anyr claude` / `anyr opencode` / `anyr codex` ([playground](https://anyrouter.dev/playground?model=deepseek/deepseek-v4.1-flash)).
- Bring your own key: [Dashboard → BYOK](https://anyrouter.dev/dashboard/byok).

Call it with your own key. AnyRouter adds no per-token charge on that path. Try it with the [Vercel AI SDK](https://anyrouter.dev/use-cases/ai-sdk); `createAnyRouter()` reads `ANYROUTER_API_KEY`:

```ts
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"

const anyrouter = createAnyRouter()

const { text } = await generateText({
  model: anyrouter("deepseek/deepseek-v4.1-flash"),
  prompt: "Rank these three refactors by risk and say why.",
})
console.log(text)
```

_generateText with the catalog id._

Or launch a coding agent through the `anyr` CLI:

### Claude Code

```bash
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr claude --model "deepseek/deepseek-v4.1-flash"
```

### OpenCode

```bash
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr opencode --model "deepseek/deepseek-v4.1-flash"
```

### Codex

```bash
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr codex --model "deepseek/deepseek-v4.1-flash"
```

More: [AI SDK](https://anyrouter.dev/use-cases/ai-sdk) · [OpenAI SDK](https://anyrouter.dev/use-cases/openai-sdk) · [coding agents](https://anyrouter.dev/use-cases/coding-agents) · [BYOK setup](https://anyrouter.dev/use-cases/byok).
