LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Llama 4 Maverick 17B 128E Instruct

meta·meta/llama-4-maverick-17b-128e-instruct-maas·GA·Open weights·llama series
Open multimodal Llama model for strong reasoning and fast responses

Llama 4 Maverick 17B 128E Instruct by meta is offered by 3 providers on this page. Public prices are shown for 2 of them. Its reference price is $0.35 per 1M input tokens and $1.15 per 1M output tokens. The lowest paid channel is IO.NET at $0.15 / $0.60 per 1M, about 2.3× below the reference price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 524,288 tokens at the reference host, but hosts report different limits, from 128,000 to 524,288, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-08.

Specs & pricing

Input / output per 1M tokens
Reference price·Vertex
$0.35 / $1.15
Blended $0.55 · Cache read —
Lowest paid·IO.NETCloud
$0.15 / $0.60
Blended $0.263 · 2.3× spread
1 more $0 channels
Context
524,288
Output limit
8,192
Knowledge cutoff
2024-08
Released / updated
2025-04-29 / 2025-04-29
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Available at 3 providers2 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Nvidia
meta/llama-4-maverick-17b-128e-instruct
First-partyFree——128,000 ⚠4,096
IO.NET
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Cloud$0.15$0.60$0.075$0.30430,000 ⚠4,096
VertexFirst-party$0.35$1.15——524,2888,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1IO.NET$51.00
2Vertex$127.50

1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Related models

Llama 3.3 70Bsame series$1.75 / $2.75Llama 4 Mavericksame series$0.20 / $0.696Llama Guard 4 12Bsame series$0.18 / $0.18Qwen3 Coder Flashcheaper alternative$0.144 / $0.574Grok 4.1 Fast (Non-Reasoning)cheaper alternative$0.20 / $0.50grok-4-fast-non-reasoningcheaper alternative$0.20 / $0.50Ministral 14Bcheaper alternative$0.20 / $0.20

Price historyone sample accumulated per data sync

Input list $0.35Output list $1.15Min blended $0.263

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-04). Each future sync adds a point, and once accumulated a line is drawn here.

Data partly from models.dev (MIT) · Vertex official docs ↗