Changelog | AI Gateway

AI Gateway - DeepSeek

Thu, 02 Jan 2025 00:00:00 GMT

Configuration: Added DeepSeek as a new provider.

AI Gateway - AI Gateway Dashboard

Tue, 17 Dec 2024 00:00:00 GMT

Updated dashboard to view performance, costs, and stats across all gateways.

AI Gateway - Bug Fixes

Fri, 13 Dec 2024 00:00:00 GMT

Bug Fixes: Fixed Anthropic errors being cached.
Bug Fixes: Fixed env.AI.run() requests using authenticated gateways returning authentication error.

AI Gateway - OpenRouter

Thu, 28 Nov 2024 00:00:00 GMT

Configuration: Added OpenRouter as a new provider.

AI Gateway - WebSockets API

Tue, 19 Nov 2024 00:00:00 GMT

Configuration: Added WebSockets API which provides a single persistent connection, enabling continuous communication.

AI Gateway - Authentication

Tue, 19 Nov 2024 00:00:00 GMT

Configuration: Added Authentication which adds security by requiring a valid authorization token for each request.

AI Gateway - Grok

Mon, 28 Oct 2024 00:00:00 GMT

Providers: Added Grok as a new provider.

AI Gateway - Vercel SDK

Thu, 17 Oct 2024 00:00:00 GMT

Added Vercel AI SDK. The SDK supports many different AI providers, tools for streaming completions, and more.

AI Gateway - Persistent logs

Thu, 26 Sep 2024 00:00:00 GMT

Logs: AI Gateway now has logs that persist, giving you the flexibility to store them for your preferred duration.

AI Gateway - Logpush

Thu, 26 Sep 2024 00:00:00 GMT

Logs: Securely export logs to an external storage location using Logpush.

AI Gateway - Pricing

Thu, 26 Sep 2024 00:00:00 GMT

Pricing: Added pricing for storing logs persistently.

AI Gateway - Evaluations

Thu, 26 Sep 2024 00:00:00 GMT

Configurations: Use AI Gateway’s Evaluations to make informed decisions on how to optimize your AI application.

AI Gateway - Custom costs

Tue, 10 Sep 2024 00:00:00 GMT

Configuration: AI Gateway now allows you to set custom costs at the request level custom costs to requests, accurately reflect your unique pricing, overriding the default or public model costs.

AI Gateway - Mistral AI

Fri, 02 Aug 2024 00:00:00 GMT

Providers: Added Mistral AI as a new provider.

AI Gateway - Google AI Studio

Tue, 23 Jul 2024 00:00:00 GMT

Providers: Added Google AI Studio as a new provider.

AI Gateway - Custom metadata

Wed, 10 Jul 2024 00:00:00 GMT

AI Gateway now supports adding custom metadata to requests, improving tracking and analysis of incoming requests.

AI Gateway - Logs

Tue, 09 Jul 2024 00:00:00 GMT

Logs are now available for the last 24 hours.

AI Gateway - Custom cache key headers

Mon, 24 Jun 2024 00:00:00 GMT

AI Gateway now supports custom cache key headers.

AI Gateway - Access an AI Gateway through a Worker

Tue, 18 Jun 2024 00:00:00 GMT

Workers AI now natively supports AI Gateway.

AI Gateway - AI Gateway is now GA

Wed, 22 May 2024 00:00:00 GMT

AI Gateway is moving from beta to GA.

AI Gateway - 2024-05-16

Thu, 16 May 2024 00:00:00 GMT

Providers: Added Cohere and Groq as new providers.

AI Gateway - 2024-05-09

Thu, 09 May 2024 00:00:00 GMT

Added new endpoints to the REST API.

AI Gateway - 2024-03-26

Tue, 26 Mar 2024 00:00:00 GMT

LLM Side Channel vulnerability fixed
Providers: Added Anthropic, Google Vertex, Perplexity as providers.

AI Gateway - 2023-10-26

Thu, 26 Oct 2023 00:00:00 GMT

Real-time Logs: Logs are now real-time, showing logs for the last hour. If you have a need for persistent logs, please let the team know on Discord. We are building out a persistent logs feature for those who want to store their logs for longer.
Providers: Azure OpenAI is now supported as a provider!
Docs: Added Azure OpenAI example.
Bug Fixes: Errors with costs and tokens should be fixed.

AI Gateway - 2023-10-09

Mon, 09 Oct 2023 00:00:00 GMT

Logs: Logs will now be limited to the last 24h. If you have a use case that requires more logging, please reach out to the team on Discord.
Dashboard: Logs now refresh automatically.
Docs: Fixed Workers AI example in docs and dash.
Caching: Embedding requests are now cacheable. Rate limit will not apply for cached requests.
Bug Fixes: Identical requests to different providers are not wrongly served from cache anymore. Streaming now works as expected, including for the Universal endpoint.
Known Issues: There's currently a bug with costs that we are investigating.