Llama 4 Maverick 17B 128e Instruct

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

Meta· 131K ctx

open weightstool call quant: unknown

spread (output, p90 ÷ p10)

1.3×

$0.600 – $1.48 · 6 providers · max÷min 2.5×

6 providers priced · 6 offerings

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published

A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.

Provider	Input	Output	Cache rd	Blended
IO.NETfp8 inference host	$0.150	$0.600	$0.0750	$0.168
Deep Infrafp8 inference host	$0.200	$0.800	—	$0.255no cache price published
NovitaAIfp8 inference host	$0.270	$0.850	—	$0.323no cache price published
Azurefp8 hyperscaler	$0.25	$1.00	—	$0.32no cache price published
Azure Cognitive Servicesfp8 hyperscaler	$0.25	$1.00	—	$0.32no cache price published
watsonx.aifp8outlier hyperscaler	$0.37	$1.48	—	$0.47no cache price published

Free tiers (rate-limited) · 1

No payment required; rate limits and quotas apply (not tracked yet). Excluded from cheapest, median and spread.

Nvidia meta/llama-4-maverick-17b-128e-instructNVIDIA developer account + API keyfree tier

Unpriced · 1

Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.

Llama llama-4-maverick-17b-128e-instruct-fp8unpriced

Connect

Provider (default: cheapest output among direct providers)

$0.600 /M · inference host

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.

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