> ## Documentation Index > Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # May May brings **more control for platform teams**: flexible config parameters, new guardrail partners, and expanded provider coverage including Claude Platform on AWS. See what's new: ## Summary | Area | Key highlights | | :- | :- | | **Gateway** | • `default_params`, `override_params`, and `drop_params` for config targets
• Usage limit policies
• Prometheus config and API key labels
• Proxy-path endpoint guardrail | | **Guardrails** | • Cato Networks
• Lakera Guard
• Tavily online checks
• CrowdStrike AIDR metadata forwarding
• Prompt Security updates | | **Models and providers** | • Claude Platform on AWS
• Vertex AI: multi-region, Anthropic batches, Gemini TTS, `service_tier`
• Amazon Bedrock: `service_tier`, prompt cache pricing
• Azure AI Foundry: native Responses API
• Multi-dimensional pricing
• Fal AI, BytePlus, Scenario AI | ## Gateway ### Default, override, and drop parameters for config targets Platform teams get three levers to control exactly what reaches the model—all in one place, without touching client code: * `default_params` — fills in a value only when the client hasn't already set it. * `drop_params` — strips fields before they reach the model, by dot-notation path. These inherit through nested targets, so org-wide defaults and workspace overrides layer cleanly on top of each other. Learn more: [Configs](/docs/docs/product/ai-gateway/configs) ### Usage limit policies Teams that need more precision than a budget policy offers now get a dedicated **usage limit policy** type—cap consumption exactly how your org plans it, across teams or workloads. ### Endpoint guardrail for proxy requests Endpoint allow/block policies now apply consistently across both the standard and proxy path—no more gaps when traffic routes differently. Learn more: [Guardrails](/docs/docs/product/guardrails) ### Circuit breaker: provider slug references Breaker rules stay stable even as providers are renamed or shared across catalogs—no more reconfiguring when a provider slug changes. ## Guardrails ### Cato Networks **Cato Networks** is now available as a guardrail to inspect LLM prompts and responses for security risks—with **monitor**, **anonymize**, or **block** actions depending on the severity of what's detected. Learn more: [Cato Networks](/docs/docs/integrations/guardrails/cato) ### Lakera Guard The new **Lakera Guard** integration detects prompt injection and redacts PII. When only PII is detected, Lakera redacts it and lets the request through; any other policy hit blocks the request. Use `project_id` to select a specific Lakera policy and `apiBase` to target regional endpoints. Learn more: [Lakera Guard](/docs/docs/integrations/guardrails/lakera) ### Tavily Online The new **Tavily** guardrail runs web-grounded checks—verifying claims against live web results before returning them to users, so your guardrail pipeline catches outdated or fabricated information. Learn more: [Tavily](/docs/docs/integrations/guardrails/tavily) ### CrowdStrike AIDR: richer context Requests to CrowdStrike AIDR now include **user ID**, **user name**, **LLM provider**, and **model** from your request metadata—giving CrowdStrike more context for policy decisions and audit trails. Learn more: [CrowdStrike AIDR](/docs/docs/integrations/guardrails/crowdstrike-aidr) ### Prompt Security Prompt security checks are extended with additional coverage and configuration options, including provider- and deployment-specific settings. ## Models and providers ### Claude Platform on AWS Anthropic's full-platform capabilities are now accessible through AWS via the new `claude-platform-aws` provider, with `accessKey`, `assumedRole`, and `serviceRole` authentication modes. Learn more: [Claude Platform (AWS)](/docs/docs/integrations/llms/claude-platform-aws) ### Vertex AI * Multi-region endpoints for batches, embeddings, Anthropic Claude on Vertex, and Gemini models * Anthropic Claude batch workloads through the unified `/v1/batches` API * Gemini text-to-speech through the unified speech APIs * OpenAI-style `service_tier` forwarded for tiered inference and usage attribution Learn more: [Vertex AI](/docs/docs/integrations/llms/vertex-ai) ### Amazon Bedrock * `service_tier` support for correct mapping and usage attribution on tiered inference * Prompt cache pricing now accounts for 1-hour cached context on Bedrock Mantle Learn more: [Amazon Bedrock](/docs/docs/integrations/llms/bedrock) ### Azure AI Foundry * Native `/v1/responses` endpoint with agent references Learn more: [Azure AI Foundry](/docs/docs/integrations/llms/azure-ai-foundry) ### Azure * Workload identity for Azure OpenAI, Azure AI Foundry, and Azure Cache for Redis ### New providers * **Fal AI** — image, video, and audio generation models * **BytePlus** — chat completions * **Scenario AI** — proxy passthrough with Basic auth ### Provider updates * **Cloudflare Workers AI** — handles OpenAI-compatible response format for newer models (Kimi K2.5, K2.6) * **Together AI** — cost now reported correctly on streamed responses * **Anthropic Messages** — tool-call argument deltas after the finish chunk are no longer dropped * **Perplexity** — long Sonar streams no longer end prematurely ## Support Open an issue on GitHub Get support in our Discord ## Related topics - [May](/docs/changelog/2025/may.md) - [Atlassian Remote MCP server](/docs/integrations/mcp-servers/atlassian-mcp-server.md) - [PII Redaction](/docs/product/guardrails/pii-redaction.md) - [9. Future Trends in LLM Cost Optimization](/docs/guides/whitepapers/optimizing-llm-costs/future-trends.md) - [Complete Logs Export](/docs/product/enterprise-offering/otel/complete-logs.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.