Home / Models / Meta / Llama 4 Maverick

Llama 4 Maverick pricing and routing profile

Llama 4 Maverick from Meta lists at $0.188 per million input tokens and $0.652 per million output tokens, with a 1,048,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.188
Output, per 1M tokens$0.652
Context window1.05M
Confidence signalAvailable

Tool callingStructured outputLog probabilities

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.119
Chat reply (2,000 in, 400 out)$0.636
Retrieval-augmented answer (8,000 in, 500 out)$1.83

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Yes. 2 of 5 tracked hosts return token log probabilities for Llama 4 Maverick, which is the confidence signal Gimbix uses to let a cheaper model answer first.

Measured by Gimbix

On 400 real BANKING77 customer messages, Llama 4 Maverick answered 294 correctly (95% interval 69.0%–77.6%), with 1 invalid answers, at $0.101 per 1,000 requests and a median of 1,154 ms. See all 22 models.

Who serves Llama 4 Maverick

HostInput / output per 1MLog probabilitiesUptime, last 30 min
DigitalOcean$0.188 / $0.652yes100.0%
DeepInfra$0.20 / $0.80no99.5%
Novita$0.27 / $0.85no100.0%
Parasail$0.35 / $1.00yes100.0%
Google$0.35 / $1.15no—

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Llama 4 Maverick that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3 VL 30B A3B Instruct$0.15 / $0.6015%
gpt-oss-120b$0.15 / $0.6015%
GPT-4o-mini$0.15 / $0.6015%
GPT-4o-mini (2024-07-18)$0.15 / $0.6015%
GLM 5.3 Flash$0.15 / $0.5021%
Qwen3.8 Omni Flash$0.15 / $0.4723%

Compare Llama 4 Maverick

Questions

How much does Llama 4 Maverick cost?

Llama 4 Maverick lists at $0.188 per million input tokens and $0.652 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.636 per 1,000 requests.

What is the context window of Llama 4 Maverick?

1,048,576 tokens.

Can a cheaper model replace Llama 4 Maverick?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Llama 4 Maverick on one half of your requests and make at most three answers worse on the other.