Llama-3.1-70B-Instruct

meta· 2024-07-23· 131K ctx· llama3.1

open weightstool callstructured quant: unknown

spread (output)

2.5×

$0.400 – $0.990 · 9 providers

9 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Kilo Gateway relay router	$0.400	$0.400	—	$0.400^*
OpenRouter unknown	$0.400	$0.400	—	$0.400^*
Vercel AI Gateway unknown	$0.720	$0.720	—	$0.720^*
Amazon Bedrock hyperscaler	$0.720	$0.720	—	$0.720^*
LLM Gateway relay router	$0.720	$0.720	—	$0.720^*
Amazon Bedrock hyperscaler	$0.720	$0.720	—	$0.720^*
DevPass (LLM Gateway) relay router	$0.720	$0.720	—	$0.720^*
CoreWeaveoutlier relay router	$0.800	$0.800	$0.800	$0.800
Merge Gatewayoutlier unknown	$0.990	$0.990	—	$0.990^*

Cheapest (output)

Kilo Gateway

$0.400 /M

opencode.json

{
  "provider": {
    "kilo": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.kilo.ai/api/gateway"
      },
      "models": {
        "meta-llama/llama-3.1-70b-instruct": {}
      }
    }
  }
}

Set KILO_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.