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

[Start](https://ailoot.ai/docs/da/) 

# Kompatibilitet

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

Hvilke API-formater Ailoot forstår, hvilke modeller der er tilgængelige i hvert format, og hvilke klienter der bruger dem.

Ailoot følger de offentlige kontrakter for tre API'er. Hvis et program kan arbejde med OpenAI, Anthropic eller Gemini og lader dig angive din egen adresse, virker det også med Ailoot — du skal blot ændre adressen og nøglen.

Alle stier er relative til adressen `https://api.ailoot.ai`. Kolonnen »SDK-adresse« viser, hvilken basisadresse du skal angive: `https://api.ailoot.ai/v1` (med /v1) eller `https://api.ailoot.ai` (uden /v1), fordi SDK'erne selv tilføjer resten af stien.

| Format | Sti | SDK-adresse | ID |
| --- | --- | --- | --- |
| OpenAI Chat Completions | `POST /v1/chat/completions` | med /v1 | 139 |
| OpenAI Responses | `POST /v1/responses` | med /v1 | 106 |
| Anthropic Messages | `POST /v1/messages` | uden /v1 | 150 |
| Gemini | `POST /v1beta/models/{m}:generateContent`<br>`POST /v1beta/models/{m}:streamGenerateContent` | uden /v1beta | 29 |
| OpenAI Embeddings | `POST /v1/embeddings` | med /v1 | 6 |
| OpenAI Images | `POST /v1/images/generations`<br>`POST /v1/images/edits` | med /v1 | 30 |
| OpenAI Audio | `POST /v1/audio/speech`<br>`POST /v1/audio/transcriptions` | med /v1 | 20 |
| Video og musik | `POST /v1/videos/generations`<br>`POST /v1/music/generations` | med /v1 | 18 |
| [Beslutninger (Jev)](https://ailoot.ai/docs/da/api/systemone/) | `POST /v1/systemone` | uden SDK, fuld adresse | 1 |
| Modelliste (OpenAI, Anthropic) | `GET /v1/models` | med /v1 | alle |
| Modelliste (Gemini) | `GET /v1beta/models` | uden /v1beta | alle |

Kataloget indeholder 1256 modelkort og 2692 dokumenterede metoder. Alternative id'er til kald eller aliaser er angivet under den valgte metode, når de findes.

## [](https://ailoot.ai/docs/da/compatibility/#models-by-format)Hvilke modeller i hvilke formater

De fleste tekstmodeller — Claude, GPT, DeepSeek, Qwen, Kimi, GLM, MiniMax og Grok — er tilgængelige i tre formater: OpenAI Chat, OpenAI Responses og Anthropic Messages. Gemini-modeller — i Anthropic Messages og det oprindelige Gemini-format. NVIDIA-modeller — hovedsageligt i 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` og yderligere [51](https://ailoot.ai/models/da/?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` og yderligere [36](https://ailoot.ai/models/da/?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` og yderligere [71](https://ailoot.ai/models/da/?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` og yderligere [13](https://ailoot.ai/models/da/?format=gemini)

Den fulde liste med priser og filtre findes i [modelkataloget](https://ailoot.ai/models/da/).

## [](https://ailoot.ai/docs/da/compatibility/#clients)Hvilke klienter bruger hvilke formater?

Nedenfor er applikationerne fra vores integrationskatalog grupperet efter det format, de bruger. Mange understøtter flere formater.

### OpenAI Chat Completions

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

### OpenAI Responses

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

### Anthropic Messages

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

### Gemini

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

## [](https://ailoot.ai/docs/da/compatibility/#features)Hvad understøttes i formaterne?

| Funktion | Sådan fungerer det |
| --- | --- |
| Streamet svar | SSE-format i alle tekstformater: `stream: true` eller `:streamGenerateContent?alt=sse`. Betalt tekst kommer i én blok efter beregning af prisen, ikke ord for ord — [læs mere](https://ailoot.ai/docs/da/how-it-works/#streaming) |
| Værktøjer (tools, function calling) | Ja, hvis modellen understøtter dem. Værktøjerne beskrives som i det valgte API. Gemini-tekstanmodninger accepterer også googleSearch og urlContext, hver for sig eller sammen, men uden functionDeclarations i samme anmodning. Ved modellens indbyggede billedoutput understøttes kun klientdefinerede `functionDeclarations` |
| Billedinput | Ja, for modeller, der kan se billeder. Den estimerede billedpris indgår i reservationen. I Gemini-format — PNG, JPEG eller WebP i `inlineData` i brugerbeskeden |
| Struktureret svar (JSON) | `response_format` i OpenAI og tilsvarende i Anthropic — hvis modellen understøtter det. I Gemini-format: `responseMimeType` accepterer text/plain eller application/json i generationConfig; brug responseSchema eller responseJsonSchema, alt efter hvad den konkrete model understøtter. Funktioner og kombinationer af parametre afhænger af modellen |
| Ræsonnering | `reasoning_effort` / `reasoning` i OpenAI, `thinking` i Anthropic, `thinkingConfig` i Gemini — for ræsonneringsmodeller |
| Optælling af tokens | Separat optælling af tokens (`/v1/messages/count_tokens`) er en selvstændig metode; tilgængeligheden kontrolleres for den valgte model og nøgle. Understøttelse af Messages bekræfter ikke i sig selv understøttelse af tokenoptælling |

Hvis modellen ikke understøtter en parameter eller et format, får du en forståelig fejl, for eksempel `unsupported_endpoint` med modellens navn. En sådan anmodning betales ikke.

Applikationer, der kalder API'et direkte fra en browserfane (visse webchats i klienttilstand), kan i øjeblikket få en CORS-fejl. Brug disse applikationers desktopversion eller servertilstand.

Har du stadig spørgsmål? Send Request ID og en beskrivelse — så hjælper vi med at finde ud af det.[Kontakt support](mailto:support@ailoot.ai)

## Ailoot · Virksomheden og dens projektportefølje





Ailoot bygger på solid driftserfaring, en stor kundebase, stabil service og løbende kontrol af KPI.





Virksomheden og dens projektportefølje: millioner af kunder; månedligt salg for milliarder.





Ailoot bruger denne driftserfaring til API-adgang til AI-funktioner i kundernes produkter, agenter, applikationer og automatiseringer.