LLaMA 4 Maverick — pricing & specs

LLaMA 4 Maverick is a balanced model from Meta, at capability tier 4 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-09-30.

$/M-token pricing

as of 2026-09-30 · OpenRouter (lowest)
Input
$0.19
per M tokens
Output
$0.65
per M tokens
Cached input
—
per M tokens

What LLaMA 4 Maverick costs in practice

At $0.65/M output tokens, LLaMA 4 Maverick is the 5th-cheapest of 9 priced tier-4 models in the Mintok catalog — about 0% below the tier median of $0.65/M.

ScenarioEst. cost
1M input + 1M output tokens$0.840
A 10K-token request (8K in / 2K out)$0.0028
1,000 agent runs (~2K in / 500 out each)$0.701
1M-token RAG chat session (900K cached in / 100K out)$0.234

Estimated from list price (as of 2026-09-30) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →

Specifications

Vendor
Meta
Family
LLaMA 4 Maverick
Capability tier
4 / 8
Size class
BALANCED
Category
GENERAL
Parameters
400B total · 1B active (MoE)
Context window
1,048,576 tokens
Licensing
Proprietary

Carbon footprint (modeled)

Energy
0.314
kWh / M-token
Emissions
151
gCO₂ / M-token

Modeled decode on a reference Cerebras Cerebras WSE-3 Turbo at 50% MBU, batch 32, global-avg grid. Compare all models & grids →

Alternatives at tier 4

Same capability tier, sorted by output price — the cheaper-capable options.

FAQ

How much does LLaMA 4 Maverick cost per token?

LLaMA 4 Maverick costs $0.19 per million input tokens and $0.65 per million output tokens, via OpenRouter (lowest), as of 2026-09-30.

Is LLaMA 4 Maverick expensive?

At $0.65/M output tokens, LLaMA 4 Maverick is the 5th-cheapest of 9 priced tier-4 models in the Mintok catalog — about 0% below the tier median of $0.65/M.

What does a typical request with LLaMA 4 Maverick cost?

At list price, a 10K-token request (8K in / 2K out) with LLaMA 4 Maverick costs about $0.0028, and 1,000 agent runs (~2K in / 500 out each) about $0.701.

What is LLaMA 4 Maverick's context window?

LLaMA 4 Maverick supports a 1,048,576-token context window.

What capability tier is LLaMA 4 Maverick?

LLaMA 4 Maverick sits at capability tier 4 of 8 on the Mintok scale (BALANCED size class).

Is LLaMA 4 Maverick open-source or proprietary?

LLaMA 4 Maverick is a proprietary model from Meta, accessed via API.

Put LLaMA 4 Maverick to work

Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.

Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.