AWS Bedrock vs OpenAI
Same workloads, both price lists, refreshed daily. On shared line items today: AWS Bedrock is cheaper on 0 of 9 shared models (input or output price), OpenAI on 6.
AWS Bedrock
Claude, Llama, Mistral, Nova and more inside AWS with IAM, VPC and compliance controls. The default when your stack already lives on AWS.
- Enterprise IAM/VPC integration
- Multiple model families
- Provisioned throughput options
OpenAI
The GPT and o-series API. Deepest ecosystem and tooling; pricing at the premium end but with aggressive batch and cached-input discounts.
- Frontier models
- Batch API at 50% off
- Prompt caching discounts
Shared models, priced by both
List prices refreshed 2026-10-08 ยท input $/1M tokens| Model | AWS Bedrock in/out | OpenAI in/out | Cheaper input |
|---|---|---|---|
| GPT-6 Luna | $0.100 / $0.500 | $0.100 / $0.500 | tie |
| GPT-5.6 Luna | $0.220 / $1.32 | $0.200 / $1.20 | OpenAI |
| GPT-6 Sol | $2.00 / $10.00 | $2.00 / $10.00 | tie |
| GPT-6.1 Sol | $2.00 / $10.00 | $2.00 / $10.00 | tie |
| GPT-5.6 Terra | $2.20 / $13.20 | $2.00 / $12.00 | OpenAI |
| GPT-5.4 | $2.75 / $16.50 | $2.50 / $15.00 | OpenAI |
| GPT-5.6 Sol | $4.40 / $22.00 | $4.00 / $20.00 | OpenAI |
| GPT-5.5 | $5.50 / $33.00 | $5.00 / $30.00 | OpenAI |
| GPT-6 Astra | $11.00 / $55.00 | $10.00 / $50.00 | OpenAI |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.