DeepInfra Llama 4 Maverick

DeepInfra Llama 4 Maverick: $0.19/1M input tokens, 860 tok/s throughput, 200ms latency. Compare on BenchNode.io.

$0.19

per 1M input tokens

$0.19 / 1M output

Free tier available

Specifications

model id: llama-4-maverick
model family: Llama 4
parameters: 400B MoE
context window tokens: 1,000,000
modality: text
reasoning: No

Performance

Latency (TTFT) 200 ms

lower is better

Uptime SLA 99.9%

Throughput 860 tok/s

200

ms latency

99.9%

uptime

Pricing Detail

input per 1m tokens usd: 0.19
output per 1m tokens usd: 0.19
free tier available: Yes
rate limit tpm: 15,000
rate limit rpm: 60

AI Analysis · gpt-4o-mini

Technical Verdict

The input and output costs of $0.19 per 1M tokens position this API tier as mid-range in price for its model class, while the throughput of 860 tok/s is relatively fast. The rate limits of 15,000 TPM and 60 RPM suggest suitability for low-volume prototyping rather than high-volume production, and the first-token latency of 200 ms favors real-time applications like chat or streaming rather than batch processing.