Llama 4 Maverick API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Llama 4 Maverick for your use-case.

Fastest

Azure (FP8)

311.7 t/s

Parasail (FP8)

99.8 t/s

DeepInfra (FP8)

44.3 t/s

Novita (FP8)

39.3 t/s

DigitalOcean

16.1 t/s

Output speed

Total 6 providers

Lowest Latency

Parasail (FP8)

0.80 s

DeepInfra (FP8)

0.83 s

DigitalOcean

1.01 s

Novita (FP8)

1.02 s

Azure (FP8)

1.34 s

Time to first token

Total 6 providers

Lowest Price

DigitalOcean

$0.17

DeepInfra (FP8)

$0.26

Parasail (FP8)

$0.29

Amazon

$0.31

Azure (FP8)

$0.33

Blended price (per 1M tokens)

Total 6 providers

Llama 4 Maverick is available through 6 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

For output speed, the top providers are Azure (FP8) (311.7 t/s), Parasail (FP8) (99.8 t/s), and DeepInfra (FP8) (44.3 t/s). Speed varies significantly across providers, with a 1832% difference between the fastest and slowest.
For latency, Parasail (FP8) (0.80s), DeepInfra (FP8) (0.83s), and DigitalOcean (1.01s) offer the lowest time to first token.
For pricing, DigitalOcean (0.17), DeepInfra (FP8) (0.26), and Parasail (FP8) (0.29) offer the lowest blended prices per 1M tokens.

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

Pricing: Cache Hit, Input, and Output: Llama 4 Maverick

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Cost per Intelligence Index Task: Llama 4 Maverick

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Output Speed vs. Price: Llama 4 Maverick

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Llama 4 Maverick

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task: Llama 4 Maverick

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

No data available

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Cost per Task vs. Time per Task: Llama 4 Maverick

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

No data available

Latency

Measured by Time (seconds) to First Token

Time to First Token: Llama 4 Maverick

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Cache Behaviour

Cache Hit Rate: Llama 4 Maverick

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Oct 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate: Llama 4 Maverick

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026

Most attractive quadrant

No data available

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time: Llama 4 Maverick

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features



Amazon Bedrock	128k	Open	--	--	--	--	--
DeepInfra	1.05M	Open	--	46	0.77	11.64	--
DigitalOcean	128k	Open	--	20	0.87	25.56	--
Microsoft Azure	128k	Open	--	194	1.59	4.17	--
Novita	1.05M	Open	--	45	1.04	12.03	--
Parasail	1.05M	Open	--	96	0.89	6.09	--

Frequently Asked Questions

Common questions about Llama 4 Maverick providers

Llama 4 Maverick is available through 6 API providers: Novita (FP8), Azure (FP8), Amazon, DeepInfra (FP8), DigitalOcean, and Parasail (FP8). Each provider offers different performance characteristics and pricing.

Llama 4 Maverick is currently available through 6 API providers that we benchmark and track.

The fastest providers for Llama 4 Maverick by output speed are Azure (FP8) (311.7 t/s), Parasail (FP8) (99.8 t/s), and DeepInfra (FP8) (44.3 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for Llama 4 Maverick are Parasail (FP8) (0.80s), DeepInfra (FP8) (0.83s), and DigitalOcean (1.01s). Lower latency means faster initial response time.

The most affordable providers for Llama 4 Maverick by blended price are DigitalOcean ($0.17 per 1M tokens), DeepInfra (FP8) ($0.26 per 1M tokens), and Parasail (FP8) ($0.29 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The providers with the lowest input token pricing for Llama 4 Maverick are DeepInfra (FP8) ($0.20 per 1M input tokens), Amazon ($0.24 per 1M input tokens), and Azure (FP8) ($0.25 per 1M input tokens).

The providers with the lowest output token pricing for Llama 4 Maverick are DeepInfra (FP8) ($0.80 per 1M output tokens), Novita (FP8) ($0.85 per 1M output tokens), and DigitalOcean ($0.87 per 1M output tokens).

Prices for Llama 4 Maverick vary up to 1.9x across providers. The most affordable is DigitalOcean at $0.17 per 1M tokens, while Novita (FP8) charges $0.33 per 1M tokens.

Output speed for Llama 4 Maverick varies significantly across providers. Azure (FP8) is the fastest at 311.7 t/s, which is 19.3x faster than DigitalOcean at 16.1 t/s.

5 of 6 providers support JSON mode for Llama 4 Maverick: Novita (FP8), Azure (FP8), DeepInfra (FP8), DigitalOcean, and Parasail (FP8).

5 of 6 providers support function calling for Llama 4 Maverick: Azure (FP8), Amazon, DeepInfra (FP8), DigitalOcean, and Parasail (FP8).

The best provider for Llama 4 Maverick depends on your priorities: Azure (FP8) offers the highest output speed, Parasail (FP8) has the lowest latency, and DigitalOcean provides the most competitive pricing.

When choosing a provider for Llama 4 Maverick, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about Llama 4 Maverick's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Llama 4 Maverick API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Pricing

Pricing: Cache Hit, Input, and Output: Llama 4 Maverick

Cache Hit

Cost per Intelligence Index Task: Llama 4 Maverick

Cost per Intelligence Index Task

Output Speed vs. Price: Llama 4 Maverick

Output Speed

Speed

Output Speed: Llama 4 Maverick

Output Speed

Model Performance Representation

Time per Intelligence Index Task: Llama 4 Maverick

Time per Intelligence Index Task

Cost per Task vs. Time per Task: Llama 4 Maverick

Cost per Intelligence Index Task

Latency

Time to First Token: Llama 4 Maverick

Latency (Time to First Token)

Median

Cache Behaviour

Cache Hit Rate: Llama 4 Maverick

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate: Llama 4 Maverick

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time: Llama 4 Maverick

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Llama 4 Maverick?

How many API providers offer Llama 4 Maverick?

Which provider is fastest for Llama 4 Maverick?

Which provider has the lowest latency for Llama 4 Maverick?

Which provider is cheapest for Llama 4 Maverick?

Which provider has the lowest input price for Llama 4 Maverick?

Which provider has the lowest output price for Llama 4 Maverick?

How much do prices vary across Llama 4 Maverick providers?

How much does speed vary across Llama 4 Maverick providers?

Which Llama 4 Maverick providers support JSON mode?

Which Llama 4 Maverick providers support function calling?

Which is the best provider for Llama 4 Maverick?

How do I choose a provider for Llama 4 Maverick?

Does provider performance for Llama 4 Maverick change over time?

What are the overall capabilities of Llama 4 Maverick?