# DeepSeek V4 Flash 0731 (NIM)

> DeepSeek-V4-Flash build 0731 on NVIDIA NIM — a dated NIM packaging of the DeepSeek V4 Flash MoE for low-latency chat and coding.

**ID**: `deepseek-ai/deepseek-v4-flash-0731`  
**Creator**: DeepSeek  
**Category**: text  
**Context**: 128K tokens  
**Status**: Removed (since 2026-08-17) — this listing is no longer sold; requests that still use `deepseek-ai/deepseek-v4-flash-0731` are routed to [`deepseek/deepseek-v4-flash`](https://anyrouter.dev/model/deepseek/deepseek-v4-flash).  
**Reason**: NVIDIA NIM smoke timeout 2026-08-17; 99% of prod errors are $0-balance with no serving BYOK. Use deepseek/deepseek-v4-flash.  
**Input**: $0.14/M  
**Output**: $0.28/M  
**Released**: 2026-07-31  
**Web page**: https://anyrouter.dev/model/deepseek-ai/deepseek-v4-flash-0731

**Input modalities**: text  
**Output modalities**: text  

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

**Supported parameters**: max_tokens, temperature, top_p, stop, tools, tool_choice

**Aliases**: `deepseek/deepseek-v4-flash-0731`

## 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-ai/deepseek-v4-flash-0731",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| nvidia | $0 | $0 |
| nvidia-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |

## Source

- Upstream docs: https://build.nvidia.com/deepseek-ai/deepseek-v4-flash-0731