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

deepseek-v4-pro is DeepSeek's flagship coding model, pairing strong agentic performance with a standout 1M-token context window and an unusually large 384K-token max output. Its competitive pricing makes frontier-class coding accessible at scale.

On Vivgrid, deepseek-v4-pro 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

Pricing

Pricing in USD per 1M tokens.

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.

Use deepseek-v4-pro in your coding agent

deepseek-v4-pro works with the same Vivgrid key and https://api.vivgrid.com/v1 endpoint as every other model in the catalog. Grab your API key from the Vivgrid Console, then drop one of the configurations below into your agent of choice.

OpenCode

OpenCode has Vivgrid built in, so you can use deepseek-v4-pro without writing any config: open /models, search for vivgrid, paste your API key and pick the model. The OpenCode tutorial walks through it step by step.

Prefer to configure it by hand? Install OpenCode:

npm i -g opencode-ai

Declare deepseek-v4-pro under the Vivgrid provider in your global OpenCode config, ~/.config/opencode/opencode.json. The @ai-sdk/openai-compatible provider talks to Vivgrid over Chat Completions (/v1/chat/completions):

{
  "$schema": "https://opencode.ai/config.json",
  "model": "vivgrid/deepseek-v4-pro",
  "provider": {
    "vivgrid": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vivgrid",
      "options": {
        "baseURL": "https://api.vivgrid.com/v1",
        "apiKey": "{env:VIVGRID_API_KEY}"
      },
      "models": {
        "deepseek-v4-pro": {
          "name": "deepseek-v4-pro",
          "tool_call": true,
          "modalities": { "input": ["text"], "output": ["text"] },
          "limit": { "context": 1000000, "output": 384000 }
        }
      }
    }
  }
}

Export your key and launch OpenCode:

export VIVGRID_API_KEY="viv-xxxxxxxxxxxxx"
opencode

Use /models to switch between deepseek-v4-pro and other Vivgrid models mid-session. See the full OpenCode tutorial.

Pi

Install Pi:

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

Add deepseek-v4-pro to the Vivgrid provider in ~/.pi/agent/models.json. Pi talks to Vivgrid over Chat Completions (/v1/chat/completions):

{
  "providers": {
    "vivgrid": {
      "baseUrl": "https://api.vivgrid.com/v1",
      "apiKey": "viv-xxxxxxxxxxxxx",
      "api": "openai-completions",
      "compat": {
        "sendSessionAffinityHeaders": true
      },
      "models": [
        {
          "id": "deepseek-v4-pro",
          "input": ["text"],
          "contextWindow": 1000000,
          "maxTokens": 384000
        }
      ]
    }
  }
}

Make it the model Pi starts with in ~/.pi/agent/settings.json:

{
  "defaultProvider": "vivgrid",
  "defaultModel": "deepseek-v4-pro"
}

Then verify and start Pi:

pi --list-models vivgrid
pi

Or run a one-shot prompt without entering the TUI:

pi -p "explain the auth flow in this repo" --model vivgrid/deepseek-v4-pro

See the full Pi tutorial.

API surfaces

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

Quick start

Get an API key from the Vivgrid Console, then call deepseek-v4-pro directly.

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

Choosing within the DeepSeek V4 family

Prices are USD per 1M tokens at the base rate. Rows marked this page are the model described here.

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-0813 — the newer 0813 release, at a lower price
• gpt-6-astra — OpenAI's frontier gpt-6 coding model
• deepseek-v4-flash — faster, cheaper V4 sibling
• deepseek-v4-flash-vision-exp — multimodal DeepSeek sibling