# DeepSeek V4.1 Flash

> DeepSeek V4.1 Flash is the cost-efficient sparse MoE tier of the V4.1 family, built on the Causal Encoder-Decoder (CED) architecture: 552B total parameters with 8B active on input and 16B on output. Native vision in, text out, 1M context. Compressed KV cache needs roughly a quarter of the previous Flash's HBM. This is the original September 2026 checkpoint, listed by OpenRouter as `deepseek/deepseek-v4.1-flash`. The official API id `deepseek-flash` now serves the October 17 snapshot, which has its own listing `deepseek/deepseek-v4.1-flash-1017`.

**ID**: `deepseek/deepseek-v4.1-flash`  
**Creator**: DeepSeek  
**Category**: text  
**Context**: 1M tokens  
**Pricing**: $0.04 / $0.14 per 1M · billed by your provider (BYOK)  
**Released**: 2026-09-10  
**Web page**: https://anyrouter.dev/model/deepseek/deepseek-v4.1-flash

**Input modalities**: text, image  
**Output modalities**: text  

**Capabilities**: chat, streaming, function-calling, coding, reasoning, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| nvidia-byok | $0.04/M (list) | $0.14/M (list) |
| openrouter-byok | $0.04/M (list) | $0.14/M (list) |
| ollama-byok | $0.04/M (list) | $0.14/M (list) |
| aihubmix-byok | $0.15/M (list) | $0.62/M (list) |
| deepinfra-byok | $0.20/M (list) | $0.60/M (list) |
| router-byok | $0.22/M (list) | $0.66/M (list) |
| vercel-byok | $0.30/M (list) | $1.20/M (list) |
| novita-byok | $0.30/M (list) | $1.20/M (list) |
| siliconflow-byok | $0.04/M (list) | $0.14/M (list) |
| gmicloud-byok | $0.30/M (list) | $1.20/M (list) |
| huggingface-byok | $0.04/M (list) | $0.14/M (list) |
| venice-byok | $0.30/M (list) | $1.20/M (list) |
| nousresearch-byok | $0.11/M (list) | $0.51/M (list) |
| baseten-byok | $0.30/M (list) | $1.20/M (list) |
| fireworks-byok | $0.30/M (list) | $1.20/M (list) |
| wafer-byok | $0.30/M (list) | $1.20/M (list) |
| onetoken-byok | $0.01/M (list) | $0.04/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.9
- **SciCode**: 0.5
- **OTIS Mock AIME**: 1.0

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).

## Source

- Upstream docs: https://api-docs.deepseek.com/quick_start/pricing