glm-5.3-flash — API, Pricing & Context Window | Vivgrid

glm-5.3-flash is Zhipu AI's lightweight sibling to glm-5.3. It trades the flagship's coding-benchmark tuning for speed and price, and adds image, video, and audio input — so the same request can reason over text alongside media. It keeps the line's 1M-token context window and 384K-token max output.

On Vivgrid, glm-5.3-flash is reachable through the unified, OpenAI-compatible endpoint, so it integrates cleanly alongside models from OpenAI, Anthropic, Google, and DeepSeek under one API key.

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.

Use glm-5.3-flash in your coding agent

glm-5.3-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 glm-5.3-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 glm-5.3-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/glm-5.3-flash",
  "provider": {
    "vivgrid": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vivgrid",
      "options": {
        "baseURL": "https://api.vivgrid.com/v1",
        "apiKey": "{env:VIVGRID_API_KEY}"
      },
      "models": {
        "glm-5.3-flash": {
          "name": "glm-5.3-flash",
          "tool_call": true,
          "attachment": true,
          "modalities": { "input": ["text", "image", "video", "audio"], "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 glm-5.3-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 glm-5.3-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": "glm-5.3-flash",
          "input": ["text", "image"],
          "contextWindow": 1000000,
          "maxTokens": 384000
        }
      ]
    }
  }
}

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

{
  "defaultProvider": "vivgrid",
  "defaultModel": "glm-5.3-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/glm-5.3-flash

See the full Pi tutorial.

API surfaces

The Vivgrid Console catalogs glm-5.3-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 glm-5.3-flash directly.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Choosing within the GLM 5.3 family

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

Ideal use cases

• High-volume, cost-sensitive agent traffic that still needs tool calling
• Multimodal steps that mix text with image, video, or audio input
• Whole-repository reasoning within a 1M-token context at low cost
• Draft or first-pass generation ahead of a flagship model's final pass

Related models

• gpt-6-astra — OpenAI's frontier gpt-6 coding model
• glm-5.3 — the flagship, text-only coding model this is derived from
• deepseek-v4-flash-vision-exp — alternative low-cost multimodal model