Llama 4 Maverick 17B 128e Instruct Fp8
MetaOpen weights1.05M context
Lowest price, from Lambda
Per million tokens
- Input
- $0.05
- Output
- $0.10
- Cached input
- —
- Batch input / output
- —
- Up to 8K output tokens per request.
Estimate your monthly cost
Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.
From Lambda: $0.70 a month.
Where to buy it (6)
Sorted by your monthly estimate. Prices per million tokens.
LambdaCheapest
- Input / output
- $0.05 / $0.10
- Context
- 131K
- Per month
- $0.70
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
DeepInfra
- Input / output
- $0.20 / $0.80
- Context
- 1.05M
- Per month
- $3.60
deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Novita AI
- Input / output
- $0.27 / $0.85
- Context
- 1.05M
- Per month
- $4.40
novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Microsoft Foundry
- Input / output
- $0.25 / $1.00
- Context
- 1M
- Per month
- $4.50
azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8
IBM watsonx
- Input / output
- $0.371 / $1.48
- Context
- 131K
- Per month
- $6.68
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Oracle Cloud
- Input / output
- $0.72 / $0.72
- Context
- 1.05M
- Per month
- $8.64
oci/meta.llama-4-maverick-17b-128e-instruct-fp8
Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Vision, Tool calling.