# Supported providers and clients Last validated Sep 30, 2026 Aperture routes model requests from clients to upstream providers. Use this reference to compare their API formats, setup options, and requirements. A provider serves models. A client or agent harness sends requests. The client, provider, and selected model must support the same API format. Matching formats does not guarantee every provider and client combination works. ## Provider matrix Provider names link to setup instructions. The table lists upstream API formats and their [compatibility flags][docs-compatibility-flags]. | Provider | API formats and flags | Base URL | | ------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- | | [OpenAI][docs-use-openai] | OpenAI Chat Completions: `openai_chat`. OpenAI Responses: `openai_responses`. | `https://api.openai.com` | | [Anthropic][docs-use-anthropic] | Anthropic Messages: `anthropic_messages`. | `https://api.anthropic.com` | | [Google Gemini][docs-use-google-gemini] | Direct Gemini: `gemini_generate_content`. | `https://generativelanguage.googleapis.com` | | [Gemini Enterprise Agent Platform (Gemini)][docs-use-geap] | Google-hosted Gemini: `google_generate_content`. Optional OpenAI Chat Completions: `openai_chat`. | `https://aiplatform.googleapis.com` | | [Gemini Enterprise Agent Platform (Anthropic)][docs-use-geap] | Google-hosted Anthropic: `google_raw_predict`. | `https://aiplatform.googleapis.com` | | [Amazon Bedrock][docs-use-amazon-bedrock] | InvokeModel: `bedrock_model_invoke`. Converse: `bedrock_converse`. | `https://bedrock-runtime..amazonaws.com` | | [Microsoft Foundry (OpenAI)][docs-use-microsoft-foundry] | OpenAI Chat Completions: `openai_chat`. OpenAI Responses: `openai_responses`. | `https://.services.ai.azure.com/api/projects//openai/` | | [Microsoft Foundry (Anthropic)][docs-use-microsoft-foundry] | Anthropic Messages: `anthropic_messages`. | `https://.services.ai.azure.com/anthropic/` | | [OpenRouter][docs-use-openrouter] | OpenAI Chat Completions: `openai_chat`. OpenAI Responses: `openai_responses`. Anthropic Messages: `anthropic_messages`. | `https://openrouter.ai/api/` | | [Vercel AI Gateway][docs-use-vercel] | OpenAI Chat Completions: `openai_chat`. OpenAI Responses: `openai_responses`. Anthropic Messages: `anthropic_messages`. | `https://ai-gateway.vercel.sh` | | [Self-hosted LLM providers][docs-use-self-hosted] | OpenAI Chat Completions: `openai_chat` by default. | Your server URL | | [Other OpenAI-compatible providers][docs-use-openai-compatible-provider] | OpenAI Chat Completions: `openai_chat` by default. The OpenAI Responses API requires upstream support and `openai_responses`. | Provider URL prefix before `/v1/...` | Set `baseurl` to the value shown. Aperture appends the full incoming request path to it. If your provider's API base URL ends in `/v1`, remove only that suffix. Keep any earlier path segments, such as OpenRouter's `/api`. Refer to [upstream URL construction][docs-aperture-configuration-url] for details. ### Provider requirements * Gemini Enterprise Agent Platform uses separate API flags for Gemini and Anthropic models. Its optional Chat Completions path is for Gemini only. The Aperture CLI labels this platform **Google Vertex**. * Bedrock InvokeModel request formats depend on the model family. The Claude Code setup uses Claude InvokeModel. Converse uses a separate format. Neither is the Anthropic Messages endpoint used by Claude Desktop. * Microsoft Foundry's OpenAI and Anthropic endpoints require separate provider configurations. * OpenRouter and Vercel AI Gateway models must support the selected API format. * [Claude subscription][docs-claude-subscriptions] and [ChatGPT subscription][docs-codex-subscriptions] credentials require their own setup. They are not interchangeable with developer API keys. When you route requests to a provider, you direct Aperture to send request content to that third-party provider. The provider's handling of that content is governed by your agreement with the provider, not your agreement with Tailscale. ## Clients and agent harnesses Choose a client that supports your provider's API. Client names link to setup instructions. **CLI** links use the Aperture CLI. **Gateway** links use settings from the Aperture gateway. | Client and setup | API formats or back ends | Requirements and limits | | -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Claude Code][docs-claude-code] ([CLI][docs-cli-claude-code], [gateway][docs-gateway-setup]) | Anthropic Messages, Claude Bedrock InvokeModel, Google-hosted Anthropic | Select the matching provider type. Subscription passthrough differs from shared API-key setup. | | [Claude Code Action][docs-claude-code-action] | Anthropic Messages | The GitHub Actions runner needs Tailscale connectivity, a CI identity, and model grants. | | [Claude Desktop][docs-claude-desktop] ([CLI][docs-cli-cowork]) | Anthropic Messages | Requires HTTPS with a trusted certificate for the gateway hostname. CLI setup, labeled **Claude Cowork**, supports macOS and Windows, not Linux. This connection is for model inference, not every desktop feature. It does not use native Bedrock APIs. | | [OpenAI Codex][docs-codex] ([CLI][docs-cli-codex], [gateway][docs-gateway-setup]) | OpenAI Responses | Chat Completions is insufficient. ChatGPT subscription passthrough uses a separate endpoint and authentication configuration. | | [OpenCode][docs-opencode] ([CLI][docs-cli-opencode], [gateway][docs-gateway-setup]) | OpenAI Responses, OpenAI Chat Completions, Anthropic Messages, native Google APIs, Bedrock | The CLI uses Google-hosted Gemini and Bedrock Converse. Gateway configuration also supports Google-hosted Anthropic and Claude InvokeModel, but not ChatGPT subscription authentication. | | [Gemini CLI][docs-cli-gemini] | Direct and Google-hosted Gemini | Version 0.40 or later requires HTTPS and a fully qualified gateway hostname. This setup uses native Google APIs, not Chat Completions. | | [GitHub Copilot CLI][docs-cli-copilot] ([gateway][docs-gateway-setup]) | OpenAI Chat Completions, OpenAI Responses, Anthropic Messages | Select the matching API mode. This entry does not cover Copilot editor integrations. | | [Pi][docs-cli-pi] ([gateway][docs-gateway-setup]) | OpenAI Responses, Anthropic Messages, OpenAI Chat Completions, Gemini | The CLI configures Google-hosted Gemini. Gateway configuration uses direct Gemini. Neither includes Bedrock. | | [Oh My Pi][docs-cli-omp] | OpenAI Responses, Anthropic Messages, OpenAI Chat Completions, Google-hosted Gemini | Uses the `omp` binary. The Google Vertex back end requires Gemini models. No Bedrock back end. | | [Hermes Agent][docs-cli-hermes] ([gateway][docs-gateway-setup]) | OpenAI Chat Completions through the CLI. Also Anthropic Messages and OpenAI Responses through gateway configuration. | Neither setup configures native Google or Bedrock APIs. | | [Kilo Code][docs-gateway-kilo] | Anthropic Messages, OpenAI Responses, OpenAI Chat Completions, native Google APIs, Bedrock InvokeModel and Converse | Gateway configuration matches back ends to APIs and model families. InvokeModel is for Claude. ChatGPT subscription authentication is excluded. | | [Grok Build][docs-gateway-grok] | OpenAI Chat Completions preferred, OpenAI Responses for models without an OpenAI Chat Completions route | Labeled **Grok** in the Aperture gateway. No Messages, native Google, or Bedrock back end. Responses routes require a compatible model response shape. | | [Aperture chat][docs-chat-setup] | Anthropic Messages, OpenAI Chat Completions, OpenAI Responses, direct and Google-hosted Gemini | Requires model access and a chat-compatible provider. Passthrough-only providers without a fallback key are unavailable. | ## Limitations * Model access depends on provider configuration and user permissions, in addition to matching API formats. * Compatibility flags describe upstream capabilities. Enabling a flag does not convert the provider to a different API. * Generic API compatibility does not cover every model feature, request field, response field, or non-chat modality. * Client-side Aperture gateway URLs and provider-side `baseurl` values are different settings. Follow the setup guide for each. * A placeholder API key cannot replace a required passthrough credential. * The Aperture CLI configures clients. Bridges and [`ts-unplug`][docs-network-access] provide network connectivity. Network connectivity and MCP connector access do not establish LLM inference compatibility. * [Tokens bought through Aperture][docs-buy-tokens] provide managed model access in built-in chat. Model availability in chat does not establish external client compatibility. ## Other providers and clients \[Missing snippet: aperture\_openai\_compatible\_provider.mdx] Groq, Together AI, Fireworks, Mistral, DeepSeek, and Perplexity are examples of the generic provider setup, not individually verified integrations. The [self-hosted provider guide][docs-use-self-hosted] covers servers such as llama.cpp, vLLM, and Ollama. Roo Code, Cline, and custom applications can use the [generic OpenAI-compatible client setup][docs-generic-clients] when their API requirements match the provider. Providers and clients not listed here might also work with these generic setups. ## Related * For compatibility flags, authorization, and pricing fields, refer to [Provider configuration][docs-provider-configuration]. * For the complete configuration schema, refer to the [Aperture configuration reference][docs-aperture-configuration]. * For step-by-step provider setup instructions, refer to the [set up LLM providers][docs-set-up-providers] guides. * To connect coding agents through Aperture, refer to the [set up LLM clients][docs-use-your-tools] guides. * For automated client configuration, refer to the [Aperture CLI][docs-cli]. * For connection and request failures, refer to [Troubleshooting Aperture][docs-troubleshooting]. [docs-compatibility-flags]: /docs/aperture/provider-compatibility#compatibility-flags [docs-aperture-configuration-url]: /docs/aperture/configuration#how-aperture-builds-upstream-urls [docs-aperture-configuration]: /docs/aperture/configuration [docs-buy-tokens]: /docs/aperture/buy-tokens-through-aperture [docs-chat-setup]: /docs/aperture/how-to/set-up-chat-ui [docs-claude-code-action]: /docs/aperture/how-to/use-claude-code-action [docs-claude-code]: /docs/aperture/how-to/use-claude-code [docs-claude-desktop]: /docs/aperture/how-to/use-claude-desktop [docs-claude-subscriptions]: /docs/aperture/how-to/use-passthrough-mode/claude-subscriptions [docs-cli-claude-code]: /docs/aperture/cli#claude-code [docs-cli-codex]: /docs/aperture/cli#openai-codex [docs-cli-copilot]: /docs/aperture/cli#github-copilot [docs-cli-cowork]: /docs/aperture/cli#claude-cowork [docs-cli-gemini]: /docs/aperture/cli#gemini-cli [docs-cli-hermes]: /docs/aperture/cli#hermes-agent [docs-cli-omp]: /docs/aperture/cli#oh-my-pi [docs-cli-opencode]: /docs/aperture/cli#opencode [docs-cli-pi]: /docs/aperture/cli#pi [docs-cli]: /docs/aperture/cli [docs-codex-subscriptions]: /docs/aperture/how-to/use-passthrough-mode/codex-subscriptions [docs-codex]: /docs/aperture/how-to/use-codex [docs-gateway-grok]: /docs/aperture/use-your-tools#grok-build [docs-gateway-kilo]: /docs/aperture/use-your-tools#kilo-code [docs-gateway-setup]: /docs/aperture/use-your-tools#gateway-generated-configuration [docs-generic-clients]: /docs/aperture/how-to/use-openai-compatible-tools [docs-network-access]: /docs/aperture/connect-outside-tailnet [docs-opencode]: /docs/aperture/how-to/use-opencode [docs-set-up-providers]: /docs/aperture/set-up-providers [docs-troubleshooting]: /docs/aperture/troubleshooting [docs-use-amazon-bedrock]: /docs/aperture/how-to/use-amazon-bedrock [docs-use-anthropic]: /docs/aperture/how-to/use-anthropic [docs-use-geap]: /docs/aperture/how-to/use-gemini-enterprise-agent-platform [docs-use-google-gemini]: /docs/aperture/how-to/use-google-gemini [docs-use-microsoft-foundry]: /docs/aperture/how-to/use-microsoft-foundry [docs-use-openai-compatible-provider]: /docs/aperture/how-to/use-openai-compatible-provider [docs-use-openai]: /docs/aperture/how-to/use-openai [docs-use-openrouter]: /docs/aperture/how-to/use-openrouter [docs-use-self-hosted]: /docs/aperture/how-to/use-self-hosted [docs-use-vercel]: /docs/aperture/how-to/use-vercel [docs-use-your-tools]: /docs/aperture/use-your-tools [docs-provider-configuration]: /docs/aperture/provider-compatibility