Cloud model platform
AWS Bedrock
Model prices vs the direct API
aws.amazon.comChecked Sep 23, 2026
- Fee on tokens
- List price
- Pass-through per 1M tokens at the lab's list price for Global cross-region inference; Geo and in-region inference cost 10% more; billed on your AWS account
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Models on AWS Bedrock
57 model routes. 25 of 50 at the lab's own list price; the rest shown as a premium or discount.
ModelHere, in / outDirectPremium
Claude Fable 5.1default region · direct $10 / $50$10 / $50same as direct$10 / $50None
GPT-6 Astraus-west-2 · direct $10 / $50$11 / $55+10% vs direct$10 / $50+10%
Claude Opus 5default region · direct $5 / $25$5 / $25same as direct$5 / $25None
Claude Opus 5eu-west-1 · direct $5 / $25$5.5 / $27.5+10% vs direct$5 / $25+10%
Claude Opus 5us-east-1 · direct $5 / $25$5.5 / $27.5+10% vs direct$5 / $25+10%
Claude Fable 5default region · direct $10 / $50$10 / $50same as direct$10 / $50None
GPT-5.6 Solus-east-1 · direct $2 / $10$4.4 / $22+120% vs direct$2 / $10+120%
Claude Opus 4.6default region · direct $5 / $25$5 / $25same as direct$5 / $25None
Claude Opus 4.7global · direct $5 / $25$5 / $25same as direct$5 / $25None
Claude Opus 4.7eu-west-1 · direct $5 / $25$5.5 / $27.5+10% vs direct$5 / $25+10%
Claude Opus 5.5default region · direct $4 / $20$4 / $20same as direct$4 / $20None
Claude Opus 5.5eu-west-1 · direct $4 / $20$4.4 / $22+10% vs direct$4 / $20+10%
Claude Opus 5.5us-east-1 · direct $4 / $20$4.4 / $22+10% vs direct$4 / $20+10%
GPT-5.5us-east-1 · direct $5 / $30$5.5 / $33+10% vs direct$5 / $30+10%
GPT-5.6 Terraus-east-1 · direct $2 / $12$2.2 / $13.2+10% vs direct$2 / $12+10%
Claude Opus 4.5default region · direct $5 / $25$5 / $25same as direct$5 / $25None
Claude Opus 4.5eu-west-1 · direct $5 / $25$5.5 / $27.5+10% vs direct$5 / $25+10%
Claude Sonnet 4.5default region · direct $3 / $15$3 / $15same as direct$3 / $15None
Claude Sonnet 4.5eu-west-1 · direct $3 / $15$3.3 / $16.5+10% vs direct$3 / $15+10%
Claude Sonnet 5global · direct $2 / $10$2 / $10same as direct$2 / $10None
Premium: blended price (3 input to 1 output) on this platform against the lab's own API. Regions are separate routes.
Features
- Fallbacks
- Load balancing
- Caching
- Guardrails
- Observability
- Rate limits
- Budgets
- Prompts
- OpenAI-compatible
- Bring your own key
- Data residency
- Private networking
What it costs on real workloads
Claude Sonnet 5$400.00vs $400.00 direct
GPT-6 Sol$400.00vs $400.00 direct
Gemini 3.8 Flash$150.00vs $150.00 direct
DeepSeek V4.1 Flash$27.00vs $27.00 direct
100M input and 20M output tokens a month, paying with gateway credits.
The terms, in their words
Managed AWS service that serves foundation models from Amazon and third-party providers through one API, billed on the customer's AWS account.
- Markup
- Pass-through per 1M tokens at the lab's list price for Global cross-region inference; Geo and in-region inference cost 10% more; billed on your AWS account
- Providers
- Pricing page lists 19 model providers (AI21 Labs, Amazon, Anthropic, Cohere, DeepSeek, Google, Luma AI, Meta, MiniMax AI, Mistral AI, Moonshot AI, NVIDIA, OpenAI, Qwen, Stability AI, TwelveLabs, Writer, xAI, Z AI)
- Amazon Bedrock offers select foundation models (FMs) from leading AI providers like Anthropic, Meta, Mistral AI, and Amazon for batch inference at a 50% lower price compared to on-demand inference pricing.
- * Priority tier pricing is at 75% premium to Standard tier pricing
- Content filters for both standard tier and classic tier (text content) $0.15 per 1,000 text units
Source: aws.amazon.com/bedrock/pricing/
AWS Bedrock vs
Pricing as read from the gateway's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.