Llama-3.1-8B-Instruct

meta· 2024-07-23· 131K ctx· llama3.1

open weights quant: unknown

spread (output)

18×

$0.025 – $0.450 · 18 providers

18 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Inference relay router	$0.025	$0.025	—	$0.025^*
Helicone relay router	$0.020	$0.030	—	$0.021^*
Kilo Gateway relay router	$0.020	$0.040	—	$0.022^*
Abacus relay router	$0.020	$0.050	—	$0.023^*
Helicone relay router	$0.020	$0.050	—	$0.023^*
NovitaAI relay router	$0.020	$0.050	—	$0.023^*
Hugging Face relay router	$0.060	$0.060	—	$0.060^*
OpenRouter unknown	$0.050	$0.080	$0.025	$0.037
NanoGPT relay router	$0.054	$0.085	$0.027	$0.040
Cortecs relay router	$0.167	$0.167	—	$0.167^*
Pioneer relay router	$0.200	$0.200	$0.200	$0.216
CoreWeave relay router	$0.220	$0.220	$0.220	$0.220
Amazon Bedrock hyperscaler	$0.220	$0.220	—	$0.220^*
Amazon Bedrock hyperscaler	$0.220	$0.220	—	$0.220^*
Merge Gateway unknown	$0.220	$0.220	—	$0.220^*
Vercel AI Gateway unknown	$0.220	$0.220	—	$0.220^*
Cloudflare Workers AIfp8 relay router	$0.152	$0.287	—	$0.164^*
Neon relay router	$0.150	$0.450	—	$0.177^*

Cheapest (output)

Inference

$0.025 /M

opencode.json

{
  "provider": {
    "inference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://inference.net/v1"
      },
      "models": {
        "meta/llama-3.1-8b-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.