Same model, served by 3 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
OpenAI Original creator | gpt-6.2-astra | standardQuantization not disclosed | $8.0 | $40.0 | $0.40 | $16.0 | Verified 2h ago · Changed 5d ago More prices
| |
AWS Bedrock | global.openai.gpt-6.2-astra | standardQuantization not disclosed | $8.0 | $40.0 | $0.40 | $16.0 | Verified 2h ago · Changed 4d ago More prices
| |
Azure AI Foundry | gpt-6.2-astra | standardglobal endpointQuantization not disclosed | $8.0 | $40.0 | $0.40 | $16.0 | Verified 21h ago · Changed 21h ago More prices
| |
AWS Bedrock | openai.gpt-6.2-astra | standardQuantization not disclosed | $8.8 | $44.0 | $0.44 | $17.6 | Verified 2h ago · Changed 4d ago More prices
| |
AWS Bedrock | us.openai.gpt-6.2-astra | standardQuantization not disclosed | $8.8 | $44.0 | $0.44 | $17.6 | Verified 2h ago · Changed 4d ago More prices
| |
Azure AI Foundry | gpt-6.2-astra | standarddata zone (US)Quantization not disclosed | $8.8 | $44.0 | $0.44 | $17.6 | Verified 21h ago · Changed 21h 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.
| OpenAI | $1,600/mo |
| AWS Bedrock | $1,600/mo |
| Azure AI Foundry global endpoint | $1,600/mo |
| AWS Bedrock | $1,760/mo |
| AWS Bedrock | $1,760/mo |
| Azure AI Foundry data zone (US) | $1,760/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.