Skip to content
CostPerPrompt

Llama 4 Maverick API Pricing

Meta · context window 524K · prices updated 2026-11-22

Input per 1M tokens
$0.35
Output per 1M tokens
$1.00
Cached input per 1M
$0.17
51% cheaper than fresh input

Where Llama 4 Maverick sits on price

At $1.00 per million output tokens, Llama 4 Maverick is a mid tier model — 2.5× cheaper than the median output price of $2.50, which puts it cheaper than 70% and pricier than 30% of the models we track. It is the most expensive of the 7 Meta models we track. Output is only 2.9× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.

Output tokens per $1
1,000,000
One full context fill
$0.1835
Cheaper than
70% of tracked models

Cached input is 51% cheaper. On an input-heavy workload you need roughly a 49% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on Llama 4 Maverick

These three workloads are the ones teams actually run on a mid-priced model — a $1.00/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0032 $47.25
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0015 $465
Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. $0.0915 $549

Model your exact traffic in the API cost calculator — it preloads Llama 4 Maverick with caching and batch options.

Llama 4 Maverick price history

Meta last raised Llama 4 Maverick's output price on Nov 5, 2026 (+53% per output token), from $0.1875/$0.6525 to $0.35/$1.00 per 1M in/out. That is one of 7 repricings in the 112 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.2 $0.8 —
Aug 10, 2026 $0.2 $0.696 -13%
Aug 14, 2026 $0.2 $0.8 +15%
Aug 31, 2026 $0.2 $0.696 -13%
Sep 15, 2026 $0.1875 $0.6525 -6%
Sep 21, 2026 $0.2 $0.8 +23%
Sep 22, 2026 $0.1875 $0.6525 -18%
Nov 5, 2026 $0.35 $1.00 +53%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Llama 4 Maverick vs Qwen2.5 VL 72B Instruct

The closest-priced alternative from another vendor is Qwen2.5 VL 72B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.45 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Qwen2.5 VL 72B Instruct pricing →

Cheaper alternatives

More Meta models

Frequently asked questions

› How much does the Llama 4 Maverick API cost?

Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens, with cached input at $0.17 per million (51% cheaper). That works out to roughly 1,000,000 output tokens per dollar.

› What does the support chatbot workload cost on Llama 4 Maverick?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0032 per request and $47.25 per month on Llama 4 Maverick. Conversation history re-sent each turn — the classic prompt-caching win.

› What does it cost to fill Llama 4 Maverick's 524K context window?

Sending 524K of input in a single request costs $0.1835 at $0.35 per million tokens — before any output. With prompt caching that same fill drops to about $0.0891 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

› Is Llama 4 Maverick worth the price?

Llama 4 Maverick sits in the middle of the market (7 of 7 by price within Meta). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.