Skip to content

Meta Llama 4 Maverick API pricing

Meta Llama 4 Maverick lists at $0.35 per 1M input tokens and $1.00 per 1M output tokens on OpenRouter. Below: its monthly cost for your workload, the provider list price where one is recorded, and each price change in the log.

Input
$0.35
Output
$1.00
Cached input
$0.17

OpenRouter, per 1M tokens. A dash means no listed price.

Your monthly cost

Your workload

90M input and 18M output tokens a month (30-day month; token counts are per request).

Assumes: 1,000 conversations a day, each sending about 3,000 tokens of history and instructions and receiving about 600 tokens of replies.

Input not in cache
$31.50
Output
$18.00
Total per month
$49.50
Per day
$1.65
Per request
$0.0016

Same prompts, other volumes

100 requests a day
$4.95 a month
1,000 requests a day
$49.50 a month
10,000 requests a day
$495 a month
Unit
Currency

The share you mark as “from cache” is billed at this model’s published cache-read price. Cache-write charges are not included. Compare this bill with other models.

Every price, with its source

OpenRouter price, per 1M tokens

Input
$0.35
Output
$1.00
Cached input (read)51% below the input price
$0.17
Context window
524,288 tokens
Maximum output
32,768 tokens
Accepts
text, image
Reasoning mode
no
Listed since
5 Apr 2025

No provider list price is recorded for this model: the figures above are what OpenRouter charges, which can differ from buying directly.

Collected from the OpenRouter models API (476 entries). 104 models are cross-checked against provider list prices in the LiteLLM price table.

Cheaper than Llama 4 Maverick for your workload

Paid models with at least Llama 4 Maverick’s context window and the same input and output types, ranked by the monthly cost of the workload you set above. Quality is not compared: test before you switch.

  • ScaleDown

    Summarize

    $3.60 a month

    93% below Llama 4 Maverick

  • ScaleDown

    Extract

    $3.60 a month

    93% below Llama 4 Maverick

  • Z.ai

    GLM Flash Latest

    $5.00 a month

    90% below Llama 4 Maverick

  • Z.ai

    GLM 5.3 Flash

    $5.00 a month

    90% below Llama 4 Maverick

Meta Llama 4 Maverick costs $49.50 a month for this workload. See the cheapest models by category.

Price history

The price changes the daily collection recorded for Meta Llama 4 Maverick, with the old and the new value.

No price change for Meta Llama 4 Maverick is in the log. A change is recorded when an input or output price moves by more than a small margin from the previous collection.

USD per 1M tokens, as listed on OpenRouter. Each line keeps the date of the collection that noticed it. All LLM API price changes.

About Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Description supplied by OpenRouter. Model id for the API: meta-llama/llama-4-maverick

Llama 4 Maverick against other models

Other Meta models

Questions and answers

How much does Meta Llama 4 Maverick cost per million tokens?

At the collection of 22 Nov 2026, 06:52 UTC, OpenRouter listed Meta Llama 4 Maverick at $0.35 per million input tokens and $1.00 per million output tokens.

What would Meta Llama 4 Maverick cost per month?

For 1,000 requests a day with 3,000 input and 600 output tokens each, over a 30-day month and with no caching, the bill is $49.50. Change the numbers in the simulator on this page to match your own traffic.

Does Meta Llama 4 Maverick have a cheaper price for cached input?

Yes. Cached input is listed at $0.17 per million tokens, 51% below the normal input price.

What is the context window of Meta Llama 4 Maverick?

524,288 tokens, with a maximum output of 32,768 tokens, as reported by OpenRouter.

Has the price of Meta Llama 4 Maverick changed?

The price history section on this page lists each change to its input or output price that the log still holds, with the old and the new value and the date of the collection that noticed it. The log starts at the oldest collection this site kept, so earlier changes are not shown. A model with no line there has no recorded change in the log.

Is Meta Llama 4 Maverick cheap for a Meta model?

By input price, Meta Llama 4 Maverick ranks 3 of 5 paid Meta models on this site, from the cheapest first. Input price alone hides the cost of long answers, so use the monthly cost on this page, which weighs input and output by your own workload, and the “Cheaper than Llama 4 Maverick” list for models with the same context and input types.