# deepseek-v4-pro-0813 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/deepseek-v4-pro-0813

deepseek-v4-pro-0813 on Vivgrid: DeepSeek's flagship coding model with a 1M-token context window, up to 384K output, and lower pricing than v4-pro.

`deepseek-v4-pro-0813` is the 0813 release of DeepSeek's flagship coding model. It keeps the line's standout **1M-token context window** and unusually large **384K-token max output**, and lands at a lower price than `deepseek-v4-pro` — **\$1.35 per 1M input tokens**, **\$0.05 cached**, and **\$3.00 output**.

It is a separate model id, not an in-place upgrade: `deepseek-v4-pro` stays available and unchanged, so you can pin either one.

On Vivgrid, `deepseek-v4-pro-0813` is available through the unified, OpenAI-compatible endpoint, so you can route DeepSeek alongside OpenAI, Anthropic, and Google models with a single API key.

## Specifications

| Field | Value |
| --- | --- |
| Provider | DeepSeek |
| Model ID | `deepseek-v4-pro-0813` |
| Best for | Coding |
| Available on | Vibe coding, Chat Completions |
| Context window | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Modalities | Text |
| Tool / function calling | Yes |
| Knowledge cutoff | 2025-05 |
| Acceleration | Global (centralized) |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $1.35 | $0.05 | $3.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.0330 |
| Warm prompt, 90% of the input served from cache | $0.00960 |


## API surfaces

The Vivgrid Console catalogs `deepseek-v4-pro-0813` on 2 surfaces, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/chat/completions` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |
| Chat Completions | `/chat/completions` | Agent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `deepseek-v4-pro-0813` directly.

```bash
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro-0813",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Cost-effective coding agents needing very long context
- Tasks that generate large outputs (up to 384K tokens)
- Whole-repository reasoning and refactoring
- High-volume engineering workloads on a budget

## Related models

- [deepseek-v4-pro](/docs/models/deepseek-v4-pro) — the prior flagship release
- [deepseek-v4-flash (0731)](/docs/models/deepseek-v4-flash) — faster, cheaper V4 sibling
- [deepseek-v4-flash-vision-exp](/docs/models/deepseek-v4-flash-vision-exp) — multimodal DeepSeek sibling