[Automated sync] Add GatewayConfig and expand AI provider support #27274
+619
−6
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sync documentation for PR #745: Add GatewayConfig and expand AI provider support This update documents the new capability to use AI Gateway with multiple AI providers (OpenAI, Anthropic, Google, Amazon Bedrock, Azure, and more) when building agents. The documentation includes: - List of 15+ supported AI providers through AI Gateway - Example code showing how to integrate AI Gateway with different providers - Reference to the AI Playground as a demonstration - Benefits of routing requests through AI Gateway (logging, caching, etc.) - Links to BYOK configuration documentation Related PR: cloudflare/agents#745 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
agents-git-bot
bot
requested review from
a team,
elithrar,
irvinebroque,
rita3ko,
thomasgauvin,
threepointone and
whoiskatrin
as code owners
github-actions
bot
added
size/s
product:agents
github-actions
bot
assigned
elithrar,
irvinebroque,
rita3ko,
thomasgauvin,
threepointone and
whoiskatrin
Contributor
|
This pull request requires reviews from CODEOWNERS as it changes files that match the following patterns:
|
Contributor
|
Preview URL: https://4ef6fb8b.preview.developers.cloudflare.com Files with changes (up to 15)
|
This documentation update corresponds to PR #745 in cloudflare/agents, which adds GatewayConfig and expands AI provider support. Changes include: - New guide: Use external AI providers in the Playground - Explains how to use OpenAI, Anthropic, and Google models - Documents two authentication methods: Provider API Key and AI Gateway - Covers model selection and MCP server integration - Updated test-remote-mcp-server.mdx to reference external provider support - Updated ai-gateway/get-started.mdx to link to the new playground guide These changes document the new user-facing features for testing AI Gateway with multiple external providers through the playground interface.
agents-git-bot
bot
requested review from
abhishekkankani,
kathayl,
mchenco,
palashgo,
roerohan and
thebongy
as code owners
agents-git-bot
bot
changed the title
- Document AI Gateway unified billing for external providers - Add examples for OpenAI, Anthropic, and Google providers - Explain provider API key (BYOK) vs unified billing options - Reference ai-gateway-provider package usage Synced from cloudflare/agents PR #745
Contributor
|
CI run failed: build logs |
Adds comprehensive documentation for using external AI providers (OpenAI, Anthropic, Google) in the Workers AI Playground, including: - New guide on external provider setup and authentication - Authentication methods: Provider API Key and AI Gateway - Available models from each provider - MCP server integration with external providers - Updated test-remote-mcp-server.mdx with cross-reference Synced from cloudflare/agents PR #745 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Contributor
Author
Documentation UpdateUpdated the PR with the following changes:
The documentation now comprehensively covers the new external provider support in the Workers AI Playground, including authentication options, model selection, and MCP server integration. All changes follow the Cloudflare Style Guide requirements and Diátaxis framework principles. |
This update adds detailed documentation for the Cloudflare AI Playground, covering the new external AI provider support and authentication methods introduced in PR #745. Key documentation additions: - External provider support (OpenAI, Anthropic, Google) - Two authentication methods: - Provider API Key (BYOK - Bring Your Own Key) - AI Gateway (Unified Billing) - Configuration options (system prompt, temperature, model filtering) - Code export examples for all authentication modes - MCP server integration guide Related PR: cloudflare/agents#745 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR syncs documentation for changes introduced in cloudflare/agents#745, which adds comprehensive external AI provider support to the Cloudflare AI Playground.
Changes
workers-ai/playground.mdx):Related PR
Source PR: cloudflare/agents#745
Key Features Documented
External Provider Support: Users can now use OpenAI (GPT-5.2, GPT-5.2 Pro, etc.), Anthropic (Claude Sonnet 4.5, Claude Opus 4.5, etc.), and Google (Gemini 3 Pro, Gemini 3 Flash, etc.) models in the Playground.
Flexible Authentication:
Enhanced User Experience:
🤖 Generated with Claude Code