gemini-3.8-flash — API, Pricing & Context Window | Vivgrid

gemini-3.8-flash is Google's newest fast Gemini model, built for agentic coding loops and multi-step tool use. It keeps the line's 1M-token context window, doubles the max output to 128K tokens, and accepts text, image, video, audio, and PDF inputs.

On Vivgrid, gemini-3.8-flash runs as a globally centralized model reachable through the same OpenAI-compatible endpoint and unified key as every other model in the catalog.

Specifications

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

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.

Input and output are priced identically to gemini-3.7-flash at $0.75 per 1M input tokens and $3.75 per 1M output tokens. Cached input is $0.15 per 1M — twice gemini-3.7-flash's introductory cached rate — so cache-heavy workloads should compare the two before switching.

Use gemini-3.8-flash in your coding agent

gemini-3.8-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 gemini-3.8-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 gemini-3.8-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/gemini-3.8-flash",
  "provider": {
    "vivgrid": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vivgrid",
      "options": {
        "baseURL": "https://api.vivgrid.com/v1",
        "apiKey": "{env:VIVGRID_API_KEY}"
      },
      "models": {
        "gemini-3.8-flash": {
          "name": "gemini-3.8-flash",
          "tool_call": true,
          "attachment": true,
          "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] },
          "limit": { "context": 1000000, "output": 128000 }
        }
      }
    }
  }
}

Export your key and launch OpenCode:

export VIVGRID_API_KEY="viv-xxxxxxxxxxxxx"
opencode

Use /models to switch between gemini-3.8-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 gemini-3.8-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",
      "models": [
        {
          "id": "gemini-3.8-flash",
          "input": ["text", "image"],
          "contextWindow": 1000000,
          "maxTokens": 128000
        }
      ]
    }
  }
}

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

{
  "defaultProvider": "vivgrid",
  "defaultModel": "gemini-3.8-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/gemini-3.8-flash

See the full Pi tutorial.

API surfaces

The Vivgrid Console catalogs gemini-3.8-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 gemini-3.8-flash directly.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Choosing within the Gemini 3 family

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

Ideal use cases

• Rapid agentic loops with heavy tool calling
• Long-form generation that needs more than a 64K output ceiling
• Long-context understanding up to 1M tokens
• High-volume multimodal reasoning and summarization

Related models

• gemini-3.7-flash — prior flash generation, cheaper cached input
• gemini-3.1-pro-preview — higher-end Gemini for coding
• claude-fable-5-1 — Anthropic's most capable model