Gemma 3 12B IT

google· 2025-03-12· 1.0M ctx

open weights quant: unknown

spread (output)

2.9×

$0.100 – $0.290 · 12 providers

12 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Helicone relay router	$0.050	$0.100	—	$0.055^*
NovitaAI relay router	$0.050	$0.100	—	$0.055^*
Hugging Face relay router	$0.050	$0.150	—	$0.059^*
Kilo Gateway relay router	$0.050	$0.150	—	$0.059^*
OpenRouter unknown	$0.050	$0.150	—	$0.059^*
Deep Infra open weights host	$0.050	$0.150	—	$0.059^*
Eden AI relay router	$0.050	$0.150	—	$0.059^*
NanoGPT relay router	$0.272	$0.272	$0.136	$0.185
Merge Gateway unknown	$0.090	$0.290	—	$0.108^*
Eden AI relay router	$0.090	$0.290	—	$0.108^*
Eden AI relay router	$0.090	$0.290	—	$0.108^*
Amazon Bedrock hyperscaler	$0.090	$0.290	—	$0.108^*

Cheapest (output)

Helicone

$0.100 /M

opencode.json

{
  "provider": {
    "helicone": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://ai-gateway.helicone.ai/v1"
      },
      "models": {
        "gemma-3-12b-it": {}
      }
    }
  }
}

Set HELICONE_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.