meta-llama/llama-4-maverick-17b-128e-instruct-fp8

meta-llama· 131K ctx

open weightstool call quant: unknown

spread (output)

2.5×

$0.600 – $1.48 · 6 providers

6 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Llamafp8 relay router	free/—	free/—	—	free/—
IO.NETfp8 relay router	$0.150	$0.600	$0.075	$0.168
Deep Infrafp8 open weights host	$0.200	$0.800	—	$0.255^*
NovitaAIfp8 relay router	$0.270	$0.850	—	$0.323^*
Azurefp8 hyperscaler	$0.250	$1.00	—	$0.318^*
Azure Cognitive Servicesfp8 unknown	$0.250	$1.00	—	$0.318^*
watsonx.aifp8outlier open weights host	$0.371	$1.48	—	$0.472^*

Cheapest (output)

IO.NET

$0.600 /M

opencode.json

{
  "provider": {
    "io-net": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.intelligence.io.solutions/api/v1"
      },
      "models": {
        "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {}
      }
    }
  }
}

Set IOINTELLIGENCE_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.