Llama 4 17B Maverick Instruct is Meta's language model with a 1.0M context window and up to 16K output tokens, available from 9 providers, starting at $0.05 / 1M input and $0.1 / 1M output. Meta's Llama 4 Maverick instruction-tuned MoE model with 17B active parameters, delivering high-performance multimodal text and image understanding.
Specifications
Canonical IDmeta-llama-4-17b-maverick-instruct
TypeLanguage
StatusActive
CreatorMetaMeta
Providers
Context Window1.0M tokens
Max Output16K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters17B
HuggingFace Likes163
HuggingFace Downloads (30d)93,997
HuggingFace Downloads (all-time)1,156,723
Knowledge Cutoff · 2 years ago

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8
$1.41$0.35
DeepInfra logo
DeepInfra
deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
$0.15$0.6
Google Vertex AI logo
Google Vertex AI
vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas
$0.35$1.15
Groq logo
Groq
groq/meta-llama/llama-4-maverick-17b-128e-instruct
$0.2$0.6
Hugging Face logo
Hugging Face
novita:meta-llama/llama-4-maverick-17b-128e-instruct-fp8
$0.27$0.85
Lambda logo
Lambda
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
$0.05$0.1
Novita logo
Novita
novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
$0.27$0.85
SambaNova logo
SambaNova
sambanova/Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80
Together AI logo
Together AI
together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.85

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 4 17B Maverick Instruct, ranked by cheapest on-demand price. The model needs about 41 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hrwestus2
g6e.xlargeAWSL40S45 GB$1.86/hrus-east-1
Standard_NV32as_v4AzureAMD Radeon Instinct MI2564 GB$1.86/hrwestus2
7 more instances can run Llama 4 17B Maverick Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 4 17B Maverick Instruct1.0M$0.050$0.100Current
Llama 3.3 70B Instruct131K$0.120$0.200Deprecating
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
Llama 3.2 11B128K$0.160$0.160Available
Llama 3.1 405B Instruct131K$0.120$0.300Deprecated
Llama 3.1 8B Instruct200K$0.020$0.030Deprecated
Llama 3.1 70B Instruct131K$0.120$0.300Available
Llama 3.1 70B128K$0.360$0.360Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Deprecated

Model IDs

azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8
deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
groq/meta-llama/llama-4-maverick-17b-128e-instruct
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
llama-4-maverick-17b-128e-instruct-maas
meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8
meta-llama-4-17b-maverick-instruct
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
publishers/google/models/llama-4-maverick-17b-128e-instruct-maas
publishers/meta/models/llama-4-maverick-17b-128e-instruct-maas
sambanova/Llama-4-Maverick-17B-128E-Instruct
together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas
vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas