M
Llama 4 MaverickOPEN
Llama 4 Maverick (Meta): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked daily against provider list prices.
- $0.35 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 52% of the 191 open-weight models tracked here
- 7 of 12 Meta models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Llama 4 Maverick, measured by Artificial Analysis. Higher is better.
For the same budget, Llama 4 Maverick delivers 5.5 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.63 per 1M tokens (median of 19) — this one costs $0.35.
Cheaper and better on this index: GLM 5.3 Flash · GPT-5.6 Luna (batch) · DeepSeek V4 Flash 0731 and 27 more
About this model
Llama 4 Maverick is an open-weight AI model by Meta. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Llama 4 Maverick?
Llama 4 Maverick is an AI language model from Meta. It is open-weight: you can download it and run it on your own hardware, for free. It scores 14.5 on the Artificial Analysis intelligence index.
Is Llama 4 Maverick free?
The weights are free and open — you can self-host Llama 4 Maverick and pay nothing per token. If you prefer a hosted API, list prices are $0.2 per million input tokens and $0.8 per million output tokens.
What is Llama 4 Maverick good at?
Independent benchmarks from Artificial Analysis give it GPQA 67.1%, MMLU-Pro 80.9%, Humanity's Last Exam 4.9%, Long Context Reasoning 50%, LiveCodeBench 39.7%, SciCode 33.1%, MATH-500 88.9%, AIME 39%, AIME 2025 19.3%, IFBench 43%, τ²-Bench 17.8%, τ-Bench Banking 3.7%, Terminal-Bench 7.9%, Terminal-Bench Hard 6.8%. It is particularly used for code generation.
How fast is Llama 4 Maverick?
It generates about 101.8 tokens per second, with a median 0.58s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Llama 4 Maverick?
Yes. Llama 4 Maverick has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.