Standard on demandon demand
$1.00input tokens$0.20per million tokens
output tokens$0.80per million tokens
Endpoint / deepinfra-meta-llama-llama-4-maverick-17b-128e-instruct-fp8
Llama 4 Maverick 17b 128e Instruct fp8
served by DeepInfra
Default workload estimate$1.001M input + 1M output tokens
- Provider model ID
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8- Protocol
- openai chat completions
- Region
- global
- Status
- active
- Base URL
https://api.deepinfra.com/v1/openai
Current offers
Price components
Exact source values; no hidden currency conversion.
Provider assertions
Claims
capability · reasoning
unsupported · 1 source assertion
compatibility · structured outputs
supported · 1 source assertion
compatibility · tools
unsupported · 1 source assertion
limits · context tokens
reported · 1 source assertion
runtime · quantization
reported · 1 source assertion
Independent checks
Observations
0
independent observations · probes begin in Stage 2
Immutable record
Pricing history
Newest observed values first.
ObservedOfferComponentPriceSnapshot