Meta logo

Llama 4 Maverick

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 4 Maverick is Meta's language model with a 1.0M context window and up to 115K output tokens, available from 5 providers, starting at $0.12 / 1M input and $0.485 / 1M output. Meta's Llama 4 Maverick MoE LLM with 128 experts and 17B active parameters, delivering high-capacity multimodal language and vision understanding.
Specifications
Canonical IDmeta-llama-4-maverick
TypeLanguage
StatusActive
CreatorMetaMeta
Providers
Context Window1.0M tokens
Max Output115K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters402B
HuggingFace Likes478
HuggingFace Downloads (30d)30,421
HuggingFace Downloads (all-time)554,732
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
#299
Coding Index
#163
Math Index
#220
MMLU-Pro
#109
GPQA
#296
HLE
#387
LiveCodeBench
#192
AIME
#75
IFBench
#236
Time to First Token
#393
SciCode
#293
MATH-500
#81
AIME 2025
#220
LCR
#235
TerminalBench Hard
#253
TAU2
#349
Output TPS
#107

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
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write 5m
$ / 1M
Input
$ / 1M
Output
$ / 1M
Databricks logo
Databricks
databricks/databricks-llama-4-maverick
$0.5$1.50$0.5$0.5——
Google Vertex AI logo
Google Vertex AI
llama-4-maverick
$0.35$1.15N/AN/A$0.175$0.575
OpenRouter logo
OpenRouter
meta-llama/llama-4-maverick
$0.188$0.652N/AN/A——
Snowflake logo
Snowflake
llama4-maverick
$0.12$0.485N/AN/A$0.06$0.242
Vercel AI Gateway logo
Vercel AI Gateway
meta/llama-4-maverick
$0.24$0.97N/AN/A——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 4 Maverick, ranked by cheapest on-demand price. The model needs about 964 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_ND96is_MI300X_v5Azure8× AMD Instinct MI300X GPU (192GB)1536 GB$48.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
p5en.48xlargeAWS8× H2001128 GB$63.30/hr
3 more instances can run Llama 4 Maverick
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
LlamaGuard 4 12B1.0M$0.180$0.180Deprecated
Llama 4 Maverick1.0M$0.120$0.485Current
Llama 4 Scout1.3M$0.100$0.300Available

Model IDs

databricks/databricks-llama-4-maverick
llama-4-maverick
meta-llama-4-maverick
meta-llama/llama-4-maverick
meta/llama-4-maverick
openrouter/meta-llama/llama-4-maverick
snowflake/llama4-maverick
vercel_ai_gateway/meta/llama-4-maverick