> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aixy-gateway.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Client protocols

> Use OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages through Aixy.

Aixy supports three client conversation formats under the same project identity and controls:
OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages. Configure your client with the
Aixy API base and project key, then choose a model available to that project.

| Client format | Typical use |
| - | - |
| Chat Completions | Existing OpenAI-compatible applications, editors, and coding agents |
| Responses | Applications using the Responses conversation and function-tool format |
| Messages | Anthropic clients and Claude Code |

OpenAI-compatible clients generally use `https://api.aixy-gateway.com/v1`. Clients such as
Claude Code that append the versioned path use the host `https://api.aixy-gateway.com`.
Follow the relevant [integration guide](/integrations/overview) for the exact client setting.

## Native requests and translation

When the client protocol matches the model's native API, Aixy preserves the native request and
response behavior, including streaming events. Otherwise, Aixy translates supported stateless
conversations and function-tool exchanges to the model's execution API and returns the requested
client format.

Choose the native format when using provider-specific capabilities. Translation covers the
supported conversation fields; stored conversation references, hosted tools, and advanced fields
require a matching execution contract. Unsupported combinations return an error instead of
silently dropping requested behavior.

For Bedrock Runtime models and inference profiles with verified native Messages support, Aixy
preserves the Messages protocol, including provider-supported tools, caching, thinking and beta
features. The API key selects the project, while the destination model determines feature support;
the same rules apply to SDKs, coding agents and other applications. Reviewed Claude models without
the direct Messages API, and verified application profiles, preserve Messages through Bedrock's
InvokeModel envelope. Aixy keeps content blocks, tool exchanges and thinking signatures in their
original format and streams events incrementally. Other conversation protocols use their matching
API or supported translation.
Native Messages support does not imply that token counting is available for the selected profile.

Bedrock Runtime imposes stricter request-metadata limits. For native Messages, Aixy keeps compatible
`metadata.user_id` values unchanged and represents valid opaque identifiers outside AWS's character
or length limits as stable SHA-256 identifiers. This affects the identifier in provider-side logs;
conversation, tool and thinking fields retain their native format. The same rule applies to every
client and does not change gateway authentication or authorization.

Beta headers also depend on the destination. On reviewed Bedrock Claude Messages routes, Aixy removes unused
announcements for `advisor-tool-2026-03-01`, `prompt-caching-scope-2026-01-05`, and
`redact-thinking-2026-02-12`. Other beta values are preserved. If the request actually uses an
advisor tool, cache scope, or thinking redaction that cannot be preserved, Aixy returns an explicit compatibility
error. Select a destination supporting that feature or disable it in the client. These rules
apply to every calling application and preserve the Messages response and streaming format.
An explicit omitted thinking display, or a reviewed omitted default, remains unchanged when an
unused redaction announcement is removed. Unknown beta values are forwarded for provider validation.

The **API Reference** tab is the source for endpoint fields and errors. Model discovery tells you
which IDs your project can address; it does not promise every provider-specific option for every
model.

## Configure and verify a client

1. Set the gateway base URL and [Aixy API key](/authentication).
2. Select an exact [model ID](/gateway/models) or [routing alias](/guides/routing).
3. Supply the conversation in the client's format and a suitable output-token bound.
4. Test text, [streaming](/guides/streaming), and any function tools your application uses.
5. Inspect Activity for the resolved provider, attempts, errors, and usage evidence.

For OpenAI GPT-5.5 and GPT-5.6, use Responses when you need function tools and reasoning together.
On Chat Completions requests containing function tools, Aixy sets reasoning effort to `none` for
those model families. Other requests keep their reasoning setting.

Function calling returns proposed tool calls to your application. Your application runs the tools
and sends their results back. To connect external tool accounts through Aixy, configure
[Agent tools and MCP](/agent-tools/overview) separately.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.