Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
AWS Bedrock | us.meta.llama4-maverick-17b-instruct-v1:0 | standardQuantization not disclosedReduced context (1M of 1M) | $0.24 | $0.97 | — | $0.422 | Verified 6h ago · Changed 6h ago | |
AWS Bedrock | meta.llama4-maverick-17b-instruct-v1:0 | standardQuantization not disclosedReduced context (1M of 1M) | $0.24 | $0.97 | — | $0.422 | Verified 6h ago · Changed 6h ago | |
Azure AI Foundry | llama-4-maverick-17b | standardglobal endpointQuantization not disclosed | $0.25 | $1.0 | — | $0.438 | Verified 4h ago · Changed 7h ago | |
Azure AI Foundry | llama-4-maverick-17b | standardeastusQuantization not disclosed | $0.275 | $1.1 | — | $0.481 | Verified 4h ago · Changed 7h ago | |
Azure AI Foundry | llama-4-maverick-17b | standarddata zone (US)Quantization not disclosed | $0.275 | $1.1 | — | $0.481 | Verified 4h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| AWS Bedrock | $43.4/mo |
| AWS Bedrock | $43.4/mo |
| Azure AI Foundry global endpoint | $45/mo |
| Azure AI Foundry eastus | $49.5/mo |
| Azure AI Foundry data zone (US) | $49.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.