Gemma 3 4B IT

google· 2025-03-12· 8K ctx· gemma

open weights quant: unknown

spread (output)

2.5×

$0.080 – $0.201 · 10 providers

10 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Eden AI relay router	$0.040	$0.080	—	$0.044^*
Eden AI relay router	$0.040	$0.080	—	$0.044^*
Merge Gateway unknown	$0.040	$0.080	—	$0.044^*
Amazon Bedrock hyperscaler	$0.040	$0.080	—	$0.044^*
OpenRouter unknown	$0.050	$0.100	—	$0.055^*
Deep Infra open weights host	$0.050	$0.100	—	$0.055^*
Eden AI relay router	$0.050	$0.100	—	$0.055^*
Hugging Face relay router	$0.050	$0.100	—	$0.055^*
Kilo Gateway relay router	$0.050	$0.100	—	$0.055^*
NanoGPToutlier relay router	$0.201	$0.201	$0.100	$0.137

Cheapest (output)

Eden AI

$0.080 /M

opencode.json

{
  "provider": {
    "edenai": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.edenai.run/v3"
      },
      "models": {
        "amazon/google.gemma-3-4b-it@us": {}
      }
    }
  }
}

Set EDENAI_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.