deepseek-v4.1-flash (1017) — API, Pricing & Context Window | Vivgrid

deepseek-v4.1-flash is the fast, ultra-affordable member of DeepSeek's V4.1 family. The model id now serves the 1017 release (October 2026), the latest checkpoint of V4.1 Flash. It keeps the V4 line's 1M-token context window and 384K-token max output, adds native image input, and is priced at $0.31 per 1M input tokens, $0.01 cached, and $1.23 output.

The 1017 release ships in place: existing deepseek-v4.1-flash requests pick it up with no config or code change. It remains a separate model id from deepseek-v4-flash, which stays available and unchanged, so you can pin either one.

It is available on both OpenAI surfaces — Chat Completions (/chat/completions) and the Responses API (/responses) — so coding CLIs that expect the Responses wire format, such as Codex and Pi, work against the same 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-v4.1-flash in your coding agent

deepseek-v4.1-flash 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-v4.1-flash 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-v4.1-flash 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-v4.1-flash",
  "provider": {
    "vivgrid": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vivgrid",
      "options": {
        "baseURL": "https://api.vivgrid.com/v1",
        "apiKey": "{env:VIVGRID_API_KEY}"
      },
      "models": {
        "deepseek-v4.1-flash": {
          "name": "deepseek-v4.1-flash",
          "tool_call": true,
          "attachment": true,
          "modalities": { "input": ["text", "image"], "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-v4.1-flash 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-v4.1-flash 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-v4.1-flash",
          "input": ["text", "image"],
          "contextWindow": 1000000,
          "maxTokens": 384000
        }
      ]
    }
  }
}

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

{
  "defaultProvider": "vivgrid",
  "defaultModel": "deepseek-v4.1-flash"
}

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-v4.1-flash

See the full Pi tutorial.

API surfaces

The Vivgrid Console catalogs deepseek-v4.1-flash on 2 surfaces, 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-v4.1-flash directly.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "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

• Very high-volume, cost-sensitive coding and agent traffic
• Tool-calling workflows that mix text with screenshots or diagrams
• Long-context summarization and extraction over whole repositories
• First-pass steps in multi-model pipelines ahead of a flagship model

Related models

• deepseek-v4-pro-0813 — DeepSeek's flagship V4 coding model