Modelspage

Llama 4 Maverick 17B Instruct

Open multimodal Llama for strong reasoning with efficient everyday serving

meta/llama-4-maverick-17b-instruct
Lab
Meta
Family
llama
Providers
18
Context
1,000,000
Output limit
16,384
Knowledge
2024-08
Release
2025-04-05
Updated
2025-04-05
Weights
Open
Input
Output types
Capabilities
tools, temperature

Providers

18
Providers
AbacusMetameta-llama/Llama-4-Maverick-17B-128E-Instruct-FP81,048,5768,192$0.14 / $0.59NoYes-Yes
Amazon BedrockMetameta.llama4-maverick-17b-instruct-v1:01,000,0008,192$0.24 / $0.97NoYesNoYes
Amazon BedrockMetaus.meta.llama4-maverick-17b-instruct-v1:01,000,0008,192$0.24 / $0.97NoYesNoYes
Deep InfraMetameta-llama/Llama-4-Maverick-17B-128E-Instruct-FP81,048,57616,384$0.20 / $0.80NoNoYesYes
DevPass (LLM Gateway)Metallama-4-maverick-17b-instruct1,048,5762,048$0.27 / $0.85NoNoNoYes
DigitalOceanMetallama-4-maverick128,00016,384$0.25 / $0.87NoYesYesYes
HeliconeMetallama-4-maverick131,0728,192$0.15 / $0.60NoYes-Yes
IO.NETMetameta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8430,0004,096$0.2688 / $0.8263NoYes-Yes
Kilo GatewayMetameta-llama/llama-4-maverick128,00016,384$0.1875 / $0.6525NoYesYesYes
LLM GatewayMetaaws-bedrock/llama-4-maverick-17b-instruct8,1922,048$0.24 / $0.97NoNoNoYes
LLM GatewayMetanovita/llama-4-maverick-17b-instruct1,048,5768,192$0.27 / $0.85NoNoNoYes
NanoGPTMetameta-llama/llama-4-maverick1,048,57665,536$0.1875 / $0.6525NoYesYesYes
NeonMetallama-4-maverick1,000,0008,192$0.50 / $1.50NoYesYesYes
Novita AIMetameta-llama/llama-4-maverick-17b-128e-instruct-fp81,048,5768,192$0.27 / $0.85NoNoYesYes
OCI Generative AIMetameta.llama-4-maverick-17b-128e-instruct-fp8512,00016,384$0.72 / $0.72NoNo-Yes
OpenRouterMetameta-llama/llama-4-maverick524,28816,384$0.1875 / $0.6525NoYesYesYes
Vercel AI GatewayMetameta/llama-4-maverick128,0008,192$0.24 / $0.97NoYes-Yes
watsonx.aiMetameta-llama/llama-4-maverick-17b-128e-instruct-fp8131,0728,192$0.371 / $1.484NoYes-Yes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Modelspage lets you browse models, compare providers, and explore rankings. Open a model for its specifications and provider prices.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints. Specialized model types are omitted by default; the site includes all model types.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

Upstream SDK

The models.dev SDK provides typed catalog queries and upstream snapshots for offline use.

Contribute

The model catalog is stored in GitHub as TOML files organized by provider and canonical model.