AWS Bedrock vs Replicate
Same workloads, both price lists, refreshed daily. On shared line items today: AWS Bedrock is cheaper on 5 of 10 shared models (input or output price), Replicate on 0.
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
Replicate
Run thousands of community models (LLMs, image, audio, video) behind one API with per-second GPU billing: the fastest path from 'found a model on GitHub' to production endpoint..
- Massive community model zoo
- Per-second billing, scale to zero
- Custom models via Cog
Shared models, priced by both
List prices refreshed 2026-08-23 ยท input $/1M tokens| Model | AWS Bedrock in/out | Replicate in/out | Cheaper input |
|---|---|---|---|
| GPT-OSS 20B | $0.075 / $0.300 | $0.090 / $0.360 | AWS Bedrock |
| GPT-OSS 120B | $0.150 / $0.600 | $0.180 / $0.720 | AWS Bedrock |
| DeepSeek V3 | $0.580 / $1.68 | $1.45 / $1.45 | AWS Bedrock |
| Claude-3.5-Haiku | $0.800 / $4.00 | $1.00 / $5.00 | AWS Bedrock |
| Claude Haiku 4.5 | $1.00 / $5.00 | $1.00 / $5.00 | tie |
| DeepSeek R1 | $1.35 / $5.40 | $3.75 / $10.00 | AWS Bedrock |
| Claude-3.7-Sonnet | $3.00 / $15.00 | $3.00 / $15.00 | tie |
| Claude Sonnet 4 | $3.00 / $15.00 | $3.00 / $15.00 | tie |
| Claude Sonnet 4.5 | $3.00 / $15.00 | $3.00 / $15.00 | tie |
| Claude-3.5-Sonnet | $3.00 / $15.00 | $3.75 / $18.75 | AWS Bedrock |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.