AISIX Cloud - AI Gateway for LLMs
API7.ai · Software Development
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
AISIX Cloud gives platform teams one governance layer for Amazon Bedrock and other LLM providers while keeping the gateway data plane in their own AWS account/VPC. Applications use OpenAI-compatible Chat Completions or Anthropic Messages APIs, while teams manage provider keys, models, policies, and usage from the AISIX-managed control plane.
Connect Amazon Bedrock, OpenAI, Anthropic, Google Vertex AI, Azure OpenAI, DeepSeek, and compatible or bring-your-own endpoints. Configure failover, round-robin, or weighted routing; retries and background health checks; virtual API keys with model allowlists; budgets with hard stops; request- and token-based rate limits; keyword or regex guardrails; and exact-match in-memory caching.
Show the rest of the publisher’s description (2 more lines)
LLM requests flow from the customer-managed data plane directly to the configured provider. Prompt and completion bodies do not pass through the AISIX-managed control plane. Operational metadata is sent over mTLS for centralized usage and cost reporting. Export OTLP/HTTP traces and Datadog request logs, and scrape local Prometheus metrics from the data plane.
The AWS Marketplace Basic plan is $149 per month and includes 1 million gateway requests. Additional requests are billed at $100 per million. LLM provider charges and AWS infrastructure costs for the customer-managed data plane are separate.
Highlights
Highlighted by the publisher on AWS Marketplace.
Customer-controlled data path - Run AISIX in your AWS account so prompt and completion bodies do not pass through the AISIX-managed control plane.
Customer-controlled data path - Run AISIX in your AWS account so prompt and completion bodies do not pass through the AISIX-managed control plane.
Production reliability and governance - Apply failover, weighted or round-robin routing, retries, budgets, rate limits, guardrails, exact-match caching, and OTLP observability.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Plans and pricing as listed
3 listed- Requests
- Requests
- Requests
Refund terms
As stated by the publisher on AWS Marketplace.
Fees are charged in accordance with the pricing details provided for each Cloud Service. If non-payment or fraud risk is suspected, monthly charges may be billed more frequently. By selecting monthly credit card billing, you authorise recurring charges. All fees must be paid in full and are non-refundable. Prices may change with website updates and apply from the stated date. Late payments may incur interest at a rate of 1% per month or the maximum permitted by law.
Sources
Linked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.