Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
AWS Bedrock Deprecated | eu.anthropic.claude-sonnet-4-20250514-v1:0 | standardQuantization not disclosedReduced context (200k of 1M) | $3.0 | $15.0 | $0.30 | $6.0 | Verified 7h ago · Changed 7h ago More prices
| |
AWS Bedrock Deprecated | apac.anthropic.claude-sonnet-4-20250514-v1:0 | standardQuantization not disclosedReduced context (200k of 1M) | $3.0 | $15.0 | $0.30 | $6.0 | Verified 7h ago · Changed 7h ago More prices
| |
AWS Bedrock Deprecated | us.anthropic.claude-sonnet-4-20250514-v1:0 | standardQuantization not disclosedReduced context (200k of 1M) | $3.0 | $15.0 | $0.30 | $6.0 | Verified 7h ago · Changed 7h ago More prices
| |
AWS Bedrock Deprecated | global.anthropic.claude-sonnet-4-20250514-v1:0 | standardQuantization not disclosedReduced context (200k of 1M) | $3.0 | $15.0 | $0.30 | $6.0 | Verified 7h ago · Changed 7h ago More prices
| |
Google Vertex AI Deprecated | claude-sonnet-4@20250514 | standardQuantization not disclosedReduced context (200k of 1M) | $3.0 | $15.0 | $0.30 | $6.0 | Verified 7h ago · Changed 7h ago More prices
|
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 | $600/mo |
| AWS Bedrock | $600/mo |
| AWS Bedrock | $600/mo |
| AWS Bedrock | $600/mo |
| Google Vertex AI | $600/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.