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

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

# Kompatibilitet

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

Hvilke API-formater Ailoot støtter, hvilke modeller som er tilgjengelige i hvert format, og hvilke klienter som bruker dem.

Ailoot følger de offentlige kontraktene til tre API-er. Hvis et program støtter OpenAI, Anthropic eller Gemini og lar deg angi en egen adresse, vil det også fungere med Ailoot — du trenger bare å endre adresse og nøkkel.

Alle endepunkter er relative til adressen `https://api.ailoot.ai`. Kolonnen «SDK-adresse» viser hva som skal angis som basisadresse: `https://api.ailoot.ai/v1` (med /v1) eller `https://api.ailoot.ai` (uten /v1), fordi SDK-ene legger til resten av endepunktet selv.

| Format | Endepunkt | 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` | uten /v1 | 150 |
| Gemini | `POST /v1beta/models/{m}:generateContent`<br>`POST /v1beta/models/{m}:streamGenerateContent` | uten /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 musikk | `POST /v1/videos/generations`<br>`POST /v1/music/generations` | med /v1 | 18 |
| [Beslutninger (Jev)](https://ailoot.ai/docs/nb/api/systemone/) | `POST /v1/systemone` | uten SDK, fullstendig adresse | 1 |
| Modelliste (OpenAI, Anthropic) | `GET /v1/models` | med /v1 | alle |
| Modelliste (Gemini) | `GET /v1beta/models` | uten /v1beta | alle |

Katalogen inneholder 1256 modellkort og 2692 dokumenterte metoder. Alternative kall-ID-er eller aliaser er oppført under den valgte metoden når de finnes.

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

De fleste tekstmodeller — Claude, GPT, DeepSeek, Qwen, Kimi, GLM, MiniMax og Grok — er tilgjengelige i tre formater: OpenAI Chat, OpenAI Responses og Anthropic Messages. Gemini-modeller er tilgjengelige i Anthropic Messages og eget Gemini-format. NVIDIA-modeller er hovedsakelig tilgjengelige 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 ytterligere [51](https://ailoot.ai/models/nb/?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 ytterligere [36](https://ailoot.ai/models/nb/?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 ytterligere [71](https://ailoot.ai/models/nb/?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 ytterligere [13](https://ailoot.ai/models/nb/?format=gemini)

Den fullstendige listen med priser og filtre finnes i [modellkatalogen](https://ailoot.ai/models/nb/).

## [](https://ailoot.ai/docs/nb/compatibility/#clients)Hvilke klienter som bruker hvilke formater

Nedenfor er apper fra integrasjonskatalogen vår, gruppert etter formatet de bruker. Mange støtter flere formater.

### OpenAI Chat Completions

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

### OpenAI Responses

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

### Anthropic Messages

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

### Gemini

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

## [](https://ailoot.ai/docs/nb/compatibility/#features)Hva formatene støtter

| Funksjon | Slik fungerer det |
| --- | --- |
| Strømmet svar | SSE i alle tekstformater: `stream: true` eller `:streamGenerateContent?alt=sse`. Betalt tekst leveres som én blokk etter at kostnaden er beregnet, ikke ord for ord — [les mer](https://ailoot.ai/docs/nb/how-it-works/#streaming) |
| Verktøy (tools, function calling) | Ja, hvis modellen støtter dem. Formatet på verktøybeskrivelsen følger det valgte API-et. Gemini-tekstforespørsler godtar også googleSearch og urlContext, hver for seg eller sammen, men ikke sammen med functionDeclarations i samme forespørsel. Native image output støtter bare klientdefinerte `functionDeclarations` |
| Bilder som inndata | Ja, for modeller som kan behandle bilder. Anslått bildekostnad inngår i reservasjonen. I Gemini-format — PNG, JPEG eller WebP i `inlineData` i brukerens melding |
| Strukturert svar (JSON) | `response_format` i OpenAI og tilsvarende i Anthropic — hvis modellen støtter det. I Gemini-format: `responseMimeType` godtar text/plain eller application/json i generationConfig; bruk responseSchema eller responseJsonSchema som støttes av den konkrete modellen. Muligheter og parameterkombinasjoner avhenger av modellen |
| Resonnering | `reasoning_effort` / `reasoning` i OpenAI, `thinking` i Anthropic, `thinkingConfig` i Gemini — for resonnerende modeller |
| Tokentelling | Separat tokentelling (`/v1/messages/count_tokens`) er en egen metode; tilgjengeligheten kontrolleres for valgt modell og nøkkel. Støtte for Messages bekrefter ikke i seg selv støtte for tokentelling |

Hvis modellen ikke støtter parameteren eller formatet, får du en forståelig feil, for eksempel `unsupported_endpoint` med modellnavnet. En slik forespørsel belastes ikke.

Apper som kaller API-et direkte fra en nettleserfane (enkelte nettchatter i klientmodus) kan nå få en CORS-feil. Bruk skrivebordsversjonen eller servermodus for slike apper.

Flere spørsmål? Send Request ID og en beskrivelse, så hjelper vi deg.[Kontakt brukerstøtte](mailto:support@ailoot.ai)

## Ailoot · Selskapet og dets prosjektportefølje





Ailoot bygger på etablert driftserfaring, en stor kundebase, stabil tjeneste og løpende KPI-kontroll.





Selskapet og dets prosjektportefølje: millioner av kunder; månedlig salg for milliarder.





Ailoot bruker denne driftserfaringen til API-tilgang til AI-funksjoner i kundenes produkter, agenter, applikasjoner og automatiseringer.