Llama 4 Maverick 17B Instruct

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

Meta· 1.0M ctx

open weights quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.720 – $0.970 · 2 providers · max÷min 1.3×

2 providers priced · 3 offerings · 1 omitted (stale)

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
Abacusfp8 router / aggregator	$0.140	$0.590	—	$0.181no cache price published
OCI Generative AIfp8 hyperscaler	$0.720	$0.720	—	$0.720no cache price published
LLM Gateway router / aggregator	$0.270	$0.850	—	$0.323no cache price published
Amazon Bedrock hyperscaler	$0.240	$0.970	—	$0.306no cache price published
Neon router / aggregator	$0.50	$1.50	—	$0.59no cache price published

Stale offerings (not in the spread) · 1

Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.

Charm Hyper llama-4-maverick-17b-128e-instruct-fp8pay per token

Subscription plans (flat fee, not per-token) · 1

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

DevPass (LLM Gateway) llama-4-maverick-17b-instructsubscription plan

Connect

Provider (default: cheapest output among direct providers)

$0.720 /M · hyperscaler

opencode.json

{
  "provider": {
    "oci": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/openai/v1"
      },
      "models": {
        "meta.llama-4-maverick-17b-128e-instruct-fp8": {}
      }
    }
  }
}

Set OCI_GENAI_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.