# Deepseek Flash (latest)

> Always resolves to the newest live Deepseek Flash model — currently DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash). DeepSeek V4.1 Flash is the cost-efficient sparse MoE tier of the V4.1 family (1M context, vision in, text out). Official API id is `deepseek-flash`; OpenRouter lists the same product as `deepseek/deepseek-v4.1-flash`.

**ID**: `deepseek/deepseek-flash-latest`  
**Creator**: DeepSeek  
**Category**: text  
**Context**: 1M tokens  
**Family alias**: always resolves to the newest live family member — currently [`deepseek/deepseek-v4.1-flash`](https://anyrouter.dev/model/deepseek/deepseek-v4.1-flash). Specs below are deepseek/deepseek-v4.1-flash's.  
**Fallback order**: `deepseek/deepseek-v4.1-flash` → `deepseek/deepseek-v4-flash`  
**Input**: $0.15/M  
**Output**: $0.62/M  
**Released**: 2026-09-10  
**Web page**: https://anyrouter.dev/model/deepseek/deepseek-flash-latest

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

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

**Aliases**: `deepseek-flash`

## 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-flash-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| nvidia-byok | $0 | $0 |
| deepseek-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| ollama-byok | $0 | $0 |
| aihubmix-byok | $0 | $0 |
| deepinfra-byok | $0 | $0 |

## Source

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