GLM-4.5V

zhipuai· 2025-08-11· 66K ctx· mit

open weightstool callreasoningstructured quant: unknown

spread (output)

2.1×

$0.860 – $1.80 · 14 providers

14 providers priced

Provider	Input	Output	Cache rd	Blended
302.AI relay router	$0.290	$0.860	—	$0.342^*
Hugging Face relay router	$0.600	$1.80	—	$0.709^*
Jiekou.AI relay router	$0.600	$1.80	—	$0.709^*
Kilo Gateway relay router	$0.600	$1.80	$0.110	$0.397
DevPass (LLM Gateway) relay router	$0.600	$1.80	$0.110	$0.397
LLM Gateway relay router	$0.600	$1.80	$0.110	$0.397
LLM Gateway relay router	$0.600	$1.80	$0.110	$0.397
Merge Gateway unknown	$0.600	$1.80	$0.110	$0.397
NanoGPT relay router	$0.600	$1.80	$0.300	$0.518
NovitaAI relay router	$0.600	$1.80	$0.110	$0.397
OpenRouter unknown	$0.600	$1.80	$0.110	$0.397
Vercel AI Gateway unknown	$0.600	$1.80	$0.110	$0.397
Z.AI relay router	$0.600	$1.80	—	$0.709^*
Zhipu AI first party lab	$0.600	$1.80	—	$0.709^*

Cheapest (output)

302.AI

$0.860 /M

opencode.json

{
  "provider": {
    "302ai": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.302.ai/v1"
      },
      "models": {
        "glm-4.5v": {}
      }
    }
  }
}

Set 302AI_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.