---
title: "API compatibility and migration"
description: "Choose the request format that matches your application and the selected model."
lastUpdated: 2026-10-22
---

Keep the request format your application already uses where the selected model supports it. Change the service address and key, then confirm exact model IDs with `GET /v1/models`. An endpoint's existence does not mean every model supports it.

| Use | Endpoint | Confirm before calling |
| --- | --- | --- |
| Available models | `GET /v1/models` | Current key and group |
| Chat | `POST /v1/chat/completions` | `model`, `messages`, streaming support |
| Responses | `POST /v1/responses` | `model`, `input`, required tool capabilities |
| Claude Messages | `POST /v1/messages` | `anthropic-version: 2023-06-01`, `max_tokens`, messages |
| Gemini | `POST /v1beta/models/{model}:generateContent` | Model in URL, `contents`; streaming uses `streamGenerateContent?alt=sse` |
| Embeddings | `POST /v1/embeddings` | Embedding model, input, dimensions |
| Reranking | `POST /v1/rerank` | Reranking model, query and documents |
| Image generation | `POST /v1/images/generations` | Image model and supported size/quality |
| Image editing | `POST /v1/images/edits` | Edit capability and required input format |
| Video | `POST /v1/videos`, `GET /v1/videos/{task_id}` | Save the ID and poll until complete |
| Realtime audio | `GET /v1/realtime?model={model}` | WebSocket, Realtime model and server-side authorization |

Use `https://infistar.ai` for international HTTPS requests and `wss://infistar.ai` for Realtime. Add `/v1` only where the client expects a versioned base address.

## Migration checks

Preserve Chat Completions for existing chat clients; use Responses for applications already built around that format. Claude and Gemini clients need their native payload shape. Never infer endpoint support from a similar model name.

Validate ordinary and streaming responses, tool calls, structured output and image input separately when your application needs them. Check response parsing, timeouts, errors and charges using a small representative request before increasing traffic. Model-specific beta fields and all vendor services are not implied by format compatibility.

See [Gateway configuration](/en/integration-guides/gateway-config), [API overview](/en/api-overview), [RAG](/en/integration-guides/rag-retrieval-quickstart), [Video](/en/api-reference/video-generation) and [Realtime](/en/api-reference/realtime-audio).