Source: https://ailoot.ai/docs/en/compatibility/
Canonical: https://ailoot.ai/docs/en/compatibility/
Language: en

[Overview](https://ailoot.ai/docs/en/) 

# Compatibility

[Markdown](https://ailoot.ai/docs/en/compatibility/index.md)

The API formats Ailoot supports, the models available in each, and the clients that use them.

Ailoot implements the public contracts of three APIs. If an application supports OpenAI, Anthropic, or Gemini and lets you set a custom URL, it can also work with Ailoot. Change the URL and key to connect.

All paths are relative to `https://api.ailoot.ai`. The SDK URL column shows the base URL to configure: `https://api.ailoot.ai/v1` (with /v1) or `https://api.ailoot.ai` (without /v1), because SDKs append the rest of the path themselves.

| Format | Path | SDK URL | ID |
| --- | --- | --- | --- |
| OpenAI Chat Completions | `POST /v1/chat/completions` | with /v1 | 139 |
| OpenAI Responses | `POST /v1/responses` | with /v1 | 106 |
| Anthropic Messages | `POST /v1/messages` | without /v1 | 150 |
| Gemini | `POST /v1beta/models/{m}:generateContent`<br>`POST /v1beta/models/{m}:streamGenerateContent` | without /v1beta | 29 |
| OpenAI Embeddings | `POST /v1/embeddings` | with /v1 | 6 |
| OpenAI Images | `POST /v1/images/generations`<br>`POST /v1/images/edits` | with /v1 | 30 |
| OpenAI Audio | `POST /v1/audio/speech`<br>`POST /v1/audio/transcriptions` | with /v1 | 20 |
| Video and music | `POST /v1/videos/generations`<br>`POST /v1/music/generations` | with /v1 | 18 |
| [Decisions (Jev)](https://ailoot.ai/docs/en/api/systemone/) | `POST /v1/systemone` | no SDK; use the full URL | 1 |
| Model list (OpenAI, Anthropic) | `GET /v1/models` | with /v1 | all |
| Model list (Gemini) | `GET /v1beta/models` | without /v1beta | all |

The catalog contains 1256 model cards and 2692 documented methods. Alternative caller IDs or aliases are listed under the selected method when available.

## [](https://ailoot.ai/docs/en/compatibility/#models-by-format)Models by API format

Most text models—Claude, GPT, DeepSeek, Qwen, Kimi, GLM, MiniMax, and Grok—are available in three formats: OpenAI Chat, OpenAI Responses, and Anthropic Messages. Gemini models are available in Anthropic Messages and native Gemini format. NVIDIA models primarily use OpenAI Chat.

### OpenAI Chat Completions

`claude-sonnet-5-5`, `gpt-6.1-sol`, `gemini-3.6-flash`, `grok-4.7`, `deepseek-v4-pro`, `qwen3.8-max`, `k3`, `glm-5.3`, `MiniMax-M3`, `nvidia/nemotron-3-ultra-550b-a55b`, `meta/muse-glimmer-30b`, `poolside/laguna-xs-2.1`, `claude-opus-5-5`, `gpt-6-astra` and another [51](https://ailoot.ai/models/en/?format=chat)

### OpenAI Responses

`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7`, `deepseek-v4-pro`, `qwen3.8-max`, `k3`, `glm-5.3`, `MiniMax-M3`, `claude-opus-5-5`, `gpt-6-astra`, `grok-4.7-build-fast`, `deepseek-v4.1-flash`, `qwen3.8-flash`, `kimi-for-coding` and another [36](https://ailoot.ai/models/en/?format=responses)

### Anthropic Messages

`claude-sonnet-5-5`, `gpt-6.1-sol`, `gemini-3.8-flash`, `grok-4.7`, `deepseek-v4-pro`, `qwen3.8-max`, `k3`, `glm-5.3`, `MiniMax-M3`, `nvidia/nemotron-3-ultra-550b-a55b`, `meta/muse-glimmer-30b`, `poolside/laguna-xs-2.1`, `claude-opus-5-5`, `gpt-6-astra` and another [71](https://ailoot.ai/models/en/?format=messages)

### Gemini

`gemini-3.8-flash`, `gemini-3.1-pro`, `gemini-pro-agent`, `gemini-3.8-flash-tiered`, `gemini-3.8-flash-medium`, `gemini-3.8-flash-low`, `gemini-3.8-flash-high`, `gemini-3.7-flash`, `gemini-3.7-flash-tiered`, `gemini-3.7-flash-medium`, `gemini-3.7-flash-low`, `gemini-3.7-flash-high`, `gemini-3.6-flash`, `gemini-3.6-flash-tiered` and another [13](https://ailoot.ai/models/en/?format=gemini)

For the full list with prices and filters, see the [model catalog](https://ailoot.ai/models/en/).

## [](https://ailoot.ai/docs/en/compatibility/#clients)Which formats clients use

Below are applications from our integration catalog, grouped by the format they use. Many support several formats.

### OpenAI Chat Completions

[Hermes Agent](https://ailoot.ai/docs/en/integrations/hermes-agent/), [OpenClaw](https://ailoot.ai/docs/en/integrations/openclaw/), [opencode](https://ailoot.ai/docs/en/integrations/opencode/), [Qwen Code](https://ailoot.ai/docs/en/integrations/qwen-code/), [Kimi CLI](https://ailoot.ai/docs/en/integrations/kimi-cli/), [Crush](https://ailoot.ai/docs/en/integrations/crush/), [Aider](https://ailoot.ai/docs/en/integrations/aider/), [Goose](https://ailoot.ai/docs/en/integrations/goose/), [Factory Droid](https://ailoot.ai/docs/en/integrations/factory-droid/), [Amp](https://ailoot.ai/docs/en/integrations/amp/), [Cline](https://ailoot.ai/docs/en/integrations/cline/), [Roo Code](https://ailoot.ai/docs/en/integrations/roo-code/), [Kilo Code](https://ailoot.ai/docs/en/integrations/kilo-code/), [Continue](https://ailoot.ai/docs/en/integrations/continue/), [Zed](https://ailoot.ai/docs/en/integrations/zed/), [VS Code + Copilot Chat](https://ailoot.ai/docs/en/integrations/vscode-copilot-byok/), [JetBrains AI Assistant](https://ailoot.ai/docs/en/integrations/jetbrains-ai-assistant/), [Xcode](https://ailoot.ai/docs/en/integrations/xcode/), [Open WebUI](https://ailoot.ai/docs/en/integrations/open-webui/), [LibreChat](https://ailoot.ai/docs/en/integrations/librechat/), [Cherry Studio](https://ailoot.ai/docs/en/integrations/cherry-studio/), [Chatbox](https://ailoot.ai/docs/en/integrations/chatbox/), [LobeChat](https://ailoot.ai/docs/en/integrations/lobechat/), [Jan](https://ailoot.ai/docs/en/integrations/jan/), [SillyTavern](https://ailoot.ai/docs/en/integrations/sillytavern/), [OpenAI SDK (Python)](https://ailoot.ai/docs/en/integrations/openai-python-sdk/), [OpenAI SDK (Node.js)](https://ailoot.ai/docs/en/integrations/openai-node-js-sdk/), [Vercel AI SDK](https://ailoot.ai/docs/en/integrations/vercel-ai-sdk/), [LangChain](https://ailoot.ai/docs/en/integrations/langchain/), [n8n](https://ailoot.ai/docs/en/integrations/n8n/), [Dify](https://ailoot.ai/docs/en/integrations/dify/), [AIChat](https://ailoot.ai/docs/en/integrations/aichat/), [AnythingLLM](https://ailoot.ai/docs/en/integrations/anythingllm/), [avante.nvim](https://ailoot.ai/docs/en/integrations/avante-nvim/), [big-AGI](https://ailoot.ai/docs/en/integrations/big-agi/), [BoltAI](https://ailoot.ai/docs/en/integrations/boltai/), [codecompanion.nvim](https://ailoot.ai/docs/en/integrations/codecompanion-nvim/), [Continue CLI](https://ailoot.ai/docs/en/integrations/continue-cli/), [CrewAI](https://ailoot.ai/docs/en/integrations/crewai/), [Flowise](https://ailoot.ai/docs/en/integrations/flowise/) and 30 more

### OpenAI Responses

[OpenAI Codex CLI](https://ailoot.ai/docs/en/integrations/openai-codex-cli/), [Hermes Agent](https://ailoot.ai/docs/en/integrations/hermes-agent/), [OpenClaw](https://ailoot.ai/docs/en/integrations/openclaw/), [Kimi CLI](https://ailoot.ai/docs/en/integrations/kimi-cli/), [Factory Droid](https://ailoot.ai/docs/en/integrations/factory-droid/), [Amp](https://ailoot.ai/docs/en/integrations/amp/), [Zed](https://ailoot.ai/docs/en/integrations/zed/), [VS Code + Copilot Chat](https://ailoot.ai/docs/en/integrations/vscode-copilot-byok/), [Cherry Studio](https://ailoot.ai/docs/en/integrations/cherry-studio/), [OpenAI SDK (Python)](https://ailoot.ai/docs/en/integrations/openai-python-sdk/), [OpenAI SDK (Node.js)](https://ailoot.ai/docs/en/integrations/openai-node-js-sdk/), [Vercel AI SDK](https://ailoot.ai/docs/en/integrations/vercel-ai-sdk/), [LangChain](https://ailoot.ai/docs/en/integrations/langchain/), [n8n](https://ailoot.ai/docs/en/integrations/n8n/), [Kilo Code CLI](https://ailoot.ai/docs/en/integrations/kilo-code-cli/), [LLM](https://ailoot.ai/docs/en/integrations/llm-cli/), [Mastra](https://ailoot.ai/docs/en/integrations/mastra/), [OpenAI Agents SDK](https://ailoot.ai/docs/en/integrations/openai-agents-sdk/), [Pydantic AI](https://ailoot.ai/docs/en/integrations/pydantic-ai/)

### Anthropic Messages

[Claude Code](https://ailoot.ai/docs/en/integrations/claude-code/), [Hermes Agent](https://ailoot.ai/docs/en/integrations/hermes-agent/), [OpenClaw](https://ailoot.ai/docs/en/integrations/openclaw/), [Qwen Code](https://ailoot.ai/docs/en/integrations/qwen-code/), [Kimi CLI](https://ailoot.ai/docs/en/integrations/kimi-cli/), [Crush](https://ailoot.ai/docs/en/integrations/crush/), [Goose](https://ailoot.ai/docs/en/integrations/goose/), [Factory Droid](https://ailoot.ai/docs/en/integrations/factory-droid/), [Amp](https://ailoot.ai/docs/en/integrations/amp/), [Cline](https://ailoot.ai/docs/en/integrations/cline/), [Roo Code](https://ailoot.ai/docs/en/integrations/roo-code/), [Zed](https://ailoot.ai/docs/en/integrations/zed/), [VS Code + Copilot Chat](https://ailoot.ai/docs/en/integrations/vscode-copilot-byok/), [LibreChat](https://ailoot.ai/docs/en/integrations/librechat/), [Cherry Studio](https://ailoot.ai/docs/en/integrations/cherry-studio/), [LobeChat](https://ailoot.ai/docs/en/integrations/lobechat/), [Jan](https://ailoot.ai/docs/en/integrations/jan/), [Anthropic SDK (Python)](https://ailoot.ai/docs/en/integrations/anthropic-python-sdk/), [Vercel AI SDK](https://ailoot.ai/docs/en/integrations/vercel-ai-sdk/), [LangChain](https://ailoot.ai/docs/en/integrations/langchain/), [n8n](https://ailoot.ai/docs/en/integrations/n8n/), [AIChat](https://ailoot.ai/docs/en/integrations/aichat/), [avante.nvim](https://ailoot.ai/docs/en/integrations/avante-nvim/), [big-AGI](https://ailoot.ai/docs/en/integrations/big-agi/), [codecompanion.nvim](https://ailoot.ai/docs/en/integrations/codecompanion-nvim/), [CrewAI](https://ailoot.ai/docs/en/integrations/crewai/), [GitHub Copilot CLI](https://ailoot.ai/docs/en/integrations/github-copilot-cli/), [gptel](https://ailoot.ai/docs/en/integrations/gptel/), [Kilo Code CLI](https://ailoot.ai/docs/en/integrations/kilo-code-cli/), [NextChat](https://ailoot.ai/docs/en/integrations/nextchat/), [Pi](https://ailoot.ai/docs/en/integrations/pi/), [Trae Agent](https://ailoot.ai/docs/en/integrations/trae-agent/), [Trae IDE](https://ailoot.ai/docs/en/integrations/trae/)

### Gemini

[OpenClaw](https://ailoot.ai/docs/en/integrations/openclaw/), [Qwen Code](https://ailoot.ai/docs/en/integrations/qwen-code/), [Gemini CLI](https://ailoot.ai/docs/en/integrations/gemini-cli/), [Kimi CLI](https://ailoot.ai/docs/en/integrations/kimi-cli/), [Amp](https://ailoot.ai/docs/en/integrations/amp/), [Vercel AI SDK](https://ailoot.ai/docs/en/integrations/vercel-ai-sdk/), [n8n](https://ailoot.ai/docs/en/integrations/n8n/), [AIChat](https://ailoot.ai/docs/en/integrations/aichat/), [Google GenAI SDK (Python)](https://ailoot.ai/docs/en/integrations/google-genai-python/), [gptel](https://ailoot.ai/docs/en/integrations/gptel/), [Pi](https://ailoot.ai/docs/en/integrations/pi/)

## [](https://ailoot.ai/docs/en/compatibility/#features)Supported features within each format

| Feature | How it works |
| --- | --- |
| Streaming responses | SSE in all text formats: `stream: true` or `:streamGenerateContent?alt=sse`. Billed text is delivered in one block after the cost is calculated, rather than word by word. See [details](https://ailoot.ai/docs/en/how-it-works/#streaming) |
| Tools (tools, function calling) | Yes, if the model supports them. Tool descriptions follow the selected API. Gemini text requests also accept googleSearch and urlContext, separately or together, but not alongside functionDeclarations in the same request. Native image output supports only client-side `functionDeclarations` |
| Image inputs | Yes, for models that can process images. The estimated image cost is included in the reserve. In Gemini format, use PNG, JPEG, or WebP in the `inlineData` field of the user message |
| Structured output (JSON) | `response_format` in OpenAI, and its equivalents in Anthropic, if supported by the model. In Gemini format, `responseMimeType` in generationConfig accepts text/plain or application/json; use responseSchema or responseJsonSchema supported by the exact model. Capabilities and parameter combinations depend on the model |
| Reasoning | `reasoning_effort` / `reasoning` in OpenAI, `thinking` in Anthropic, `thinkingConfig` in Gemini, for reasoning models |
| Token counting | Separate token counting (`/v1/messages/count_tokens`) is a separate method; its availability is checked for the selected model and key. Messages support alone does not confirm support for token counting |

If a model does not support a parameter or format, you receive a clear error, such as `unsupported_endpoint` with the model name. That request is not billed.

Applications that call the API directly from a browser tab, such as some web chats in client mode, may currently receive a CORS error. Use their desktop version or server mode instead.

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.[Contact support](mailto:support@ailoot.ai)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.