Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
OpenAI Original creator | gpt-6.1-terra | standardQuantization not disclosed | $1.0 | $5.0 | $0.05 | $2.0 | Verified 12h ago · Changed 26d ago More prices
| |
AWS Bedrock | global.openai.gpt-6.1-terra | standardQuantization not disclosed | $1.0 | $5.0 | $0.05 | $2.0 | Verified 12h ago · Changed 25d ago More prices
| |
AWS Bedrock | us.openai.gpt-6.1-terra | standardQuantization not disclosed | $1.1 | $5.5 | $0.055 | $2.2 | Verified 12h ago · Changed 25d ago More prices
| |
AWS Bedrock | openai.gpt-6.1-terra | standardQuantization not disclosed | $1.1 | $5.5 | $0.055 | $2.2 | Verified 12h ago · Changed 25d 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 | $200/mo |
| AWS Bedrock | $200/mo |
| AWS Bedrock | $220/mo |
| AWS Bedrock | $220/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.