Llama 4 Maverick 17B Instruct

meta· 2025-04-05· 131K ctx

open weightstool call quant: unknown

spread (output)

2.7×

$0.590 – $1.62 · 9 providers

9 providers priced · 1 omitted (stale)

Provider	Input	Output	Cache rd	Blended
Abacusfp8 relay router	$0.140	$0.590	—	$0.181^*
OCI Generative AIfp8 relay router	$0.720	$0.720	—	$0.720^*
LLM Gatewayoutlier relay router	$0.270	$0.850	—	$0.323^*
DevPass (LLM Gateway) relay router	$0.270	$0.850	—	$0.323^*
Charm Hyperfp8stale relay router	$0.274	$0.899	—	$0.342^*
Amazon Bedrock hyperscaler	$0.240	$0.970	—	$0.306^*
LLM Gatewayoutlier relay router	$0.240	$0.970	—	$0.306^*
Amazon Bedrock hyperscaler	$0.240	$0.970	—	$0.306^*
Neonoutlier relay router	$0.500	$1.50	—	$0.591^*
LLM Gatewayoutlier relay router	$0.530	$1.62	—	$0.629^*

Cheapest (output)

Abacus

$0.590 /M

opencode.json

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

Set ABACUS_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.