meta-llama/llama-3.2-3b-instruct

meta-llama· 131K ctx· llama3.2

open weights quant: unknown

spread (output)

17×

$0.020 – $0.335 · 9 providers

9 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Inference relay router	$0.020	$0.020	—	$0.020^*
NanoGPT relay router	$0.031	$0.049	$0.015	$0.023
LLM Gateway relay router	$0.030	$0.050	—	$0.032^*
DevPass (LLM Gateway) relay router	$0.030	$0.050	—	$0.032^*
NovitaAI relay router	$0.030	$0.050	—	$0.032^*
Kilo Gateway relay router	$0.050	$0.330	—	$0.075^*
OpenRouter unknown	$0.050	$0.330	—	$0.075^*
Pioneer relay router	$0.100	$0.335	$0.100	$0.130
Cloudflare Workers AI relay router	$0.051	$0.335	—	$0.077^*

Cheapest (output)

Inference

$0.020 /M

opencode.json

{
  "provider": {
    "inference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://inference.net/v1"
      },
      "models": {
        "meta/llama-3.2-3b-instruct": {}
      }
    }
  }
}

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

Output $/M over time7-day preview

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

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

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