Meta: Llama 4 Maverick
Llama 4 Maverick is a language model from Meta released on Jan 1, 2025. It reads text and images and writes text, with a 1.05M token context window and up to 66K tokens per reply.
Show moreShow less
It costs $0.1875 per million input tokens and $0.6525 per million output tokens. Cached input bills at $0.05, 73% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
5 providers serve it, including Vercel AI Gateway, Helicone and Kilo Gateway. The lowest input price is $0.15 per million tokens at Helicone.
On the Artificial Analysis Intelligence Index it scores 10, which places it at number 39 among the 43 models I track with independent scores.
- Modalities
- In / out price
- $0.1875 / $0.6525 per 1M
- Context
- 1.05M
- Max output
- 66K
- Released
- Jan 1, 2025
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Llama 4 Maverick pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.1875 / 1M tokens | |
|---|---|---|
| Output | $0.6525 / 1M tokens | |
| Cached input (read) | $0.05 / 1M tokens | 73% off input |
Llama 4 Maverick providers
5 providers serve it, including Vercel AI Gateway, Helicone and Kilo Gateway. The lowest input price is $0.15 per million tokens at Helicone. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Vercel AI Gateway | n/a | n/a | – | 128K | 4K |
| Helicone | $0.15 | $0.60 | – | 131K | 8K |
| Kilo Gateway | $0.1875 | $0.6525 | $0.05 | 128K | 16K |
| NanoGPT | $0.1875 | $0.6525 | $0.05 | 1.05M | 66K |
| DigitalOcean | $0.25 | $0.87 | $0.05 | 128K | 16K |
What Llama 4 Maverick costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by Meta. Each links to its source and shows the date I checked it.
A composite of 10 independent evaluations (agents 30%, coding 20%, scientific reasoning 20%, general 30%), run by Artificial Analysis on each model, version 4.3.2.
Artificial Analysis, checked Oct 10, 2026
Median output tokens per second measured by Artificial Analysis on the provider API, for the same model setting as its index score.
Artificial Analysis, checked Oct 10, 2026
Benchmarks Meta reports (5)
- gpqa-diamond (GPQA Diamond, 0-shot, accuracy, instruction tuned)69.8%
- mmlu-pro (MMLU Pro, 0-shot, macro_avg/acc)80.5%
- livecodebench (LiveCodeBench (10/01/2024-02/01/2025), 0-shot, pass@1)43.4%
- mmmu (MMMU, 0-shot, accuracy)73.4%
- mmmu-pro (MMMU Pro, 0-shot, average of Standard and Vision tasks)59.6%
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call Llama 4 Maverick through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs
Alternatives to Llama 4 Maverick
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 39.5
Reads text and images. Tool calling, structured output, reasoning. Served by 56 providers.
by deepseekSep 10, 20261M context$0.15/M input tokens$0.60/M output tokens56 providers
- Index 11.3
Reads text and images. Tool calling, structured output, reasoning. Served by 17 providers.
by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens17 providers
- Index 41.8
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 65 providers.
by z-aiAug 21, 20261M context$0.15/M input tokens$0.50/M output tokens65 providers
- Index 39.8
Reads text, images and video. Tool calling, structured output, reasoning. Served by 23 providers.
by qwenAug 26, 20261M context$0.15/M input tokens$0.47/M output tokens23 providers
- Index 14.7
Reads text and images. Tool calling, structured output, reasoning. Served by 42 providers.
by googleApr 2, 2026262K context$0.14/M input tokens$0.40/M output tokens42 providers
- 131K context
Reads text and images. Tool calling, structured output, reasoning. Served by 3 providers.
by nvidiaOct 28, 2025$0.20/M input tokens$0.60/M output tokens3 providers
More from Meta
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by metaOct 12, 2026$4/M input tokens$20/M output tokens7 providers
- Index 48.1
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 13 providers.
by metaSep 2, 20261.05M context$1.25/M input tokens$4.25/M output tokens13 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 4 providers.
by metaSep 2, 2026$0.10/M input tokens$0.20/M output tokens4 providers
Muse Image 1.0
ImageGenerates images from text and images.
by metaAug 26, 2026
- Index 17.5
Reads text and images. Reasoning.
by metaAug 10, 2026128K context
- 131K context
Reads text and images. Tool calling, structured output, reasoning. Served by 12 providers.
by metaAug 10, 2026$0.35/M input tokens$1.50/M output tokens12 providers
Llama 4 Maverick questions
How much does the Llama 4 Maverick API cost?
$0.1875 per million input tokens and $0.6525 per million output tokens, with cached input at $0.05. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Llama 4 Maverick?
1,048,576 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Llama 4 Maverick?
5 providers serve it, including Vercel AI Gateway, Helicone and Kilo Gateway. The lowest input price is $0.15 per million tokens at Helicone. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Llama 4 Maverick support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Llama 4 Maverick open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Llama 4 Maverick released?
Jan 1, 2025.
How good is Llama 4 Maverick compared with other models?
It scores 10 on the Artificial Analysis Intelligence Index. Benchmarks are a shortlist, not a verdict: test the top two or three candidates on your own tasks before you commit.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on Llama 4 Maverick?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting