Continue.dev avec Claude, GPT et Gemini

Ajoutez une entrée models au config.yaml de Continue avec provider openai et la base URL avots, et l'assistant VS Code ou JetBrains tourne sur avots.

Obtenir une clé API ✦ Voir les tarifs Docs on GitHub

Connect in three fields

Continue lit les modèles depuis config.yaml. Ajoutez un fournisseur openai qui pointe vers avots.

FieldValue
Base URLhttps://api.avots.ai/openai/v1
API keyav_mcp_… · get your key
Modelanthropic/claude-sonnet-4.6 or any id from the table below

Setup

1. Ouvrez config.yaml

Ouvrez ~/.continue/config.yaml, le format de configuration actuel de Continue. Sous Windows, c'est le dossier .continue dans votre profil utilisateur.

2. Ajoutez un modèle openai

Ajoutez une entrée sous models avec provider openai, apiBase pointant vers la base URL avots, votre clé av_mcp_, et l'id du modèle.

3. Rechargez et choisissez le modèle

Enregistrez, rechargez Continue, et choisissez le nouveau modèle dans le menu déroulant de l'assistant.

~/.continue/config.yaml
models:
  - name: Claude Sonnet (avots)
    provider: openai
    model: anthropic/claude-sonnet-4.6
    apiBase: https://api.avots.ai/openai/v1
    apiKey: av_mcp_YOUR_KEY

provider doit être openai (l'adaptateur générique compatible OpenAI), pas anthropic, sinon Continue appelle l'API Anthropic native. Gardez /v1 sur apiBase. config.yaml remplace l'ancien config.json ; si des erreurs de streaming ou de Responses-API apparaissent, ajoutez useResponsesApi: false.

Example request

curl
curl https://api.avots.ai/openai/v1/chat/completions \
  -H "Authorization: Bearer av_mcp_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Model and MCP tools in one config

Continue keeps the chat provider and MCP servers in the same file, so you paste both at once and get Claude, GPT and Gemini plus the avots creative tools (image, video, audio, talking avatars) on one av_mcp_ key. You save it yourself, nothing is added automatically.

~/.continue/config.yaml, model + MCP tools
models:
  - name: Claude Sonnet (avots)
    provider: openai
    model: anthropic/claude-sonnet-4.6
    apiBase: https://api.avots.ai/openai/v1
    apiKey: av_mcp_YOUR_KEY

mcpServers:
  - name: avots
    type: streamable-http
    url: https://mcp.avots.ai/
    requestOptions:
      headers:
        Authorization: Bearer av_mcp_YOUR_KEY

MCP setup guide →

Models and prices

Set the model field to any id below, or a lazy name like claude / gpt / gemini that maps to a sensible default.

ModelBest for⚡ / 1M tokens (in / out)
openai/gpt-5.5-proMax intelligence, hardest tasks60 000 / 360 000
anthropic/claude-opus-5Top Claude, long reasoning10 000 / 50 000
anthropic/claude-sonnet-4.6Balanced (default)6 000 / 30 000
google/gemini-3.1-pro-previewFresh Gemini Pro4 000 / 24 000
google/gemini-2.5-proStable Gemini Pro2 500 / 20 000
anthropic/claude-haiku-4.5Fast Claude2 000 / 10 000
deepseek/deepseek-r1Cheap reasoning1 400 / 5 000
google/gemini-2.5-flashFast and cheap600 / 5 000
openai/gpt-5-miniCheap OpenAI500 / 4 000
openai/gpt-oss-120b:freeFree (OpenAI open model, needs a positive balance)Free

* Price in ⚡ per 1,000,000 tokens, input / output (1000⚡ ≈ $1). Free models need a positive balance. Full list via GET /openai/v1/models.

Continue.dev avec Claude, GPT et Gemini

Generate an av_mcp_ key in Settings, paste three fields, and reach 40+ models on one balance. The same key works for MCP.

Obtenir une clé API ✦
FAQ

Questions

config.yaml ou config.json ?
config.yaml est le format actuel et masque tout ancien config.json. Mettez le modèle avots sous la liste models.
Pourquoi provider openai pour Claude ?
Parce qu'avots est compatible OpenAI. provider openai utilise le chemin /chat/completions ; provider anthropic contournerait avots.
VS Code et JetBrains tous les deux ?
Oui. Continue partage le même config.yaml entre les deux IDE.
Comment est-ce facturé ?
À la requête depuis votre solde avots.
Does it support function calling and tools?
Yes. The endpoint forwards the standard OpenAI tools, tool_choice and parallel_tool_calls fields (and the legacy functions/function_call), in both streaming and non-streaming mode, so agent frameworks like LangChain, LlamaIndex, Langflow and n8n get real tool_calls back. Whether a given request uses tools depends on the model you pick: Claude, GPT and Gemini all support function calling.

Autres clients

OpenAI-compatible API

avots speaks the OpenAI API. Any app that talks to ChatGPT through base URL, key and model…

Open WebUI with Claude, GPT and Gemini

Add avots under Connections as an OpenAI API provider, and every avots model shows up in y…

LibreChat with Claude, GPT and Gemini

Add one custom endpoint block to librechat.yaml and avots appears as a provider with every…

Cursor with Claude, GPT and Gemini

Override the OpenAI base URL in Cursor Settings, Models, paste your av_mcp_ key, add a mod…

Python openai SDK with avots

Pass base_url and your av_mcp_ key to the official openai Python client, then call any mod…

openclaw with Claude, GPT and Gemini

Add an OpenAI-compatible provider to openclaw.json pointing at avots, and openclaw runs an…

Hermes with Claude, GPT and Gemini

Set the OpenAI base URL and your av_mcp_ key in Hermes, pick a model, and it runs on avots…

Cline with Claude, GPT and Gemini

Pick OpenAI Compatible in Cline settings, paste the avots base URL and your av_mcp_ key, t…

Aider with Claude, GPT and Gemini

Export two environment variables and launch Aider with an openai/ model prefix, and the CL…

SillyTavern with Claude, GPT and Gemini

Choose Custom (OpenAI-compatible) as the Chat Completion source in SillyTavern, paste the …

AnythingLLM with Claude, GPT and Gemini

Choose Generic OpenAI as the LLM provider in AnythingLLM, fill the avots base URL, key, mo…

Node.js openai SDK with avots

Pass baseURL and your av_mcp_ key to the official openai client, then call any model by id…

Chatbox with Claude, GPT and Gemini

Add a custom OpenAI API compatible provider in Chatbox, paste the avots host and your av_m…

Obtenir une clé