# DeepSeek V4 Pro API

> DeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an open-weight preview in April 2026 with a 1M-token context. It combines token-wise compression with DeepSeek Sparse Attention and supports thinking and non-thinking modes, aimed at agentic coding, advanced reasoning and knowledge-heavy work. On DeepSeek's API this name now serves the August 2026 GA revision; use the 0813 entry to pin that version.

Source: https://www.sandbase.ai/models/deepseek/deepseek-v4-pro
API reference: https://www.sandbase.ai/models/deepseek/deepseek-v4-pro/docs

## Facts

- Provider: DeepSeek
- Type: Language model
- Model ID: `deepseek/deepseek-v4-pro`
- Price: $0.99 per 1M input tokens, $2.97 per 1M output tokens (25% off list price)
- Context window: 1M tokens, up to 384K output tokens
- Capabilities: chat, reasoning, structured output, function calling
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Chat Completions API: `POST https://api.sandbase.ai/v1/chat/completions`

```bash
curl -X POST https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}'
```

## FAQ

### How do I call DeepSeek V4 Pro through SandBase?

Create a SandBase API key, then send requests with the model ID "deepseek/deepseek-v4-pro" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### How much does DeepSeek V4 Pro cost?

$0.99 per 1M input tokens and $2.97 per 1M output tokens with the current 25% discount (list price $1.32 / $3.96), billed per request from your SandBase balance.

### What is the context window of DeepSeek V4 Pro?

1M tokens of context, with up to 384K output tokens per response.

### How does DeepSeek V4 Pro score on benchmarks?

DeepSeek V4 Pro scores 36.0 on the Artificial Analysis Intelligence Index (v4.3), ranking #31 of 83 models on SandBase; Coding Index 68.8, Agentic Index 41.3. Source: Artificial Analysis, measured as DeepSeek V4 Pro 0813 (Max).

### Which features does DeepSeek V4 Pro support?

DeepSeek V4 Pro supports reasoning, function calling, structured output. See Specifications above for the full list.

### Do I need a separate DeepSeek account?

No. One SandBase API key and balance gives you access to DeepSeek V4 Pro and the other models in the catalog; you do not need to sign up with DeepSeek separately.