You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: changelog/2025/may.mdx
+8-5Lines changed: 8 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,7 +20,7 @@ Here’s everything new this month:
20
20
|**Improvements**| • Token cost tracking for gpt-image-1<br/>• Ping messages removed from streamed responses<br/>• Resizing metadata columns in logs |
21
21
|**New models & providers**| • Claude 4 now live<br/>• PDF support for Claude via Anthropic and Bedrock<br/>• OpenAI’s Computer Use Tool supported via Responses API<br/>• Grok 3 and Grok 3 Mini on Azure<br/>• Gemini 2.5 Thinking Mode in Prompt Playground<br/>• Extended thinking for Claude 3.7 and Claude 4<br/>• Mistral supports function calling<br/>• WorkersAI supports image generation<br/>• Lepton AI, Nscale now integrated<br/>• Tool calling enabled for Mistral and OpenRouter<br/>• MIME type support for Vertex and Google<br/>• PDF support via Anthropic and Bedrock |
22
22
|**Guardrails**| • Prompt Security guardrails for injection detection and sensitive data protection<br/>• JWT validator input guardrail<br/>• PANW Prisma AIRS plugin for real-time prompt/response risk blocking<br/>• Model whitelist guardrail for org/environment/request-level control |
23
-
|**Documentation**| • Guardrail documentation moved under “Integrations”<br/>• New solution pages for AWS Bedrock and GovCloud<br/>• Cookbook: OpenAI Computer Use tool <br/>• Cookbook: Optimizing Prompts using LLama Prompt Ops |
23
+
|**Documentation**| • Guardrail documentation moved under “Integrations”<br/>• New solution pages for AWS Bedrock and GovCloud<br/>• Cookbook: OpenAI Computer Use tool <br/>• Cookbook: Optimizing Prompts using LLama Prompt Ops |
24
24
---
25
25
26
26
## AI agent infrastructure
@@ -76,7 +76,10 @@ For teams consolidating observability into Arize, you can now view Portkey’s l
76
76
</Frame>
77
77
More than half of Fortune 500 companies use Azure OpenAI. But building GenAI apps in the enterprise is still messy, cost attribution, routing logic, usage tracking, model evaluation... all scattered.
78
78
79
-
With Portkey’s deep integration into the Azure AI ecosystem (OpenAI, Foundry, APIM, Marketplace), teams can now build, scale, and govern GenAI apps without leaving their existing cloud setup. <br><br>Our customers are vouching for it!
79
+
With Portkey’s deep integration into the Azure AI ecosystem (OpenAI, Foundry, APIM, Marketplace), teams can now build, scale, and govern GenAI apps without leaving their existing cloud setup.
@@ -99,7 +102,7 @@ Start using Portkey with [Claude Code](https://portkey.ai/docs/integrations/libr
99
102
100
103
**AI coding assistants**
101
104
102
-
Plug Portkey into [Cline](https://portkey.ai/docs/integrations/libraries/cline) or [Roo Code](https://portkey.ai/docs/integrations/libraries/roo-code) and enable:
105
+
Plug Portkey into [Cline](https://portkey.ai/docs/integrations/libraries/cline) or [Roo Code](https://portkey.ai/docs/integrations/libraries/roo-code) and enable:
103
106
104
107
- Access to the latest models from OpenAI, Anthropic, Mistral, and more
105
108
- Full observability—log every prompt, tool use, and response with metadata
@@ -205,10 +208,10 @@ Build production-grade browser automation with enterprise-level controls. Our la
205
208
206
209
From powering reliable provider failovers at Hedy to equipping AI policy analysts, Portkey is becoming the trusted backbone for builders!
0 commit comments