# Evanesca

> Evanesca is a private AI agent and chat — a European alternative to ChatGPT. It runs AI models from Mistral AI, the Swiss AI Initiative, Qwen, DeepSeek, Z.ai, OpenAI, Meta and Google in Europe, searches the web, writes documents and creates images, and keeps no copy of your messages. It works in the browser, costs only what you use (credit from €2, no subscription), and shows a passport under every answer: model, operator, place, law, and what was kept.

Published by FLEECE AI (SASU, SIREN 932 329 188), Chamalières, France. Third-party policies checked on 2026-09-29; the catalogue and the chat's features on 2026-10-20.

Status: the chat app opens soon; https://evanesca.app/chat is a waiting page. This site describes how it will work.

## Key facts
- What it is: an AI agent and chat in the browser. Agent mode carries out a task step by step — web search, the conversation's files, Word, PDF and Excel documents, images — and never runs code; each task stops at a spending cap the user sets (€2 by default, from €0.50 to €10). Its files stay in the user's browser.
- Models run in Europe: 17. In France by OVHcloud (AI Endpoints, Gravelines) and Scaleway (Generative APIs, Paris); in Mistral AI's EU region; in Germany by AKI.IO (AKI.IO GmbH, Berlin, which says its inference runs on GPU infrastructure in German data centres); in Switzerland by Infomaniak (outside the EU, under an EU adequacy decision). OVHcloud, Scaleway, Mistral AI and Infomaniak are European companies with no US parent; AKI.IO is a German company whose shareholders are not published. Mistral Large 4 has no published weights yet; the others are open-weight. Evanesca serves no model outside Europe, and no model call falls back to a server outside Europe.
- Web search (off by default, in the chat and in Agent mode; a switch): the model's queries and the pages it reads go to Linkup Technologies, a French company (registered office in Fresnes; Evanesca has not verified where its servers run); the conversation itself is not sent, though a query can repeat words of a message. Billed per call — €0.0076 per search and €0.0015 per page read, VAT included — plus the pages read, as input tokens.
- Image generation: FLUX.1 [schnell] (Black Forest Labs) and PhotoMaker V2 (TencentARC), run by Infomaniak in Switzerland, billed per second of generation (€0.00924 per second, VAT included). Generated images carry IPTC metadata marking them as AI-generated (AI Act art. 50(2)); it is metadata, not a watermark, so a screenshot or a re-encode can remove it.
- Dictation: Mistral AI's Voxtral (Mistral AI, a French company, keeps the audio 30 days against abuse), billed per second. Read-aloud uses the device's own voices: the text never leaves it. Memory is off by default and kept in the browser.
- What Evanesca keeps: no prompts and no answers (held in memory only while the answer is written). Conversation history stays in the user's browser. About messages, Evanesca keeps only billing data (tokens and cost); account and payment data are kept as the law requires.
- What the operators keep: OVHcloud says "Zero data retention: We keep only the data required for billing purposes." Scaleway applies zero data retention by default; when requests cause errors or look abusive, it may keep and read their content for up to 14 days. Mistral AI keeps API inputs and outputs "for thirty (30) rolling days to monitor abuse" (Mistral Large 4, Mistral Small 4 and dictation). AKI.IO says "prompts, inputs, and generated outputs are processed in volatile memory and are not logged, stored, or analyzed"; it keeps usage metadata (request ID, timestamps, token usage) for 90 days. Infomaniak states that queries are "neither recorded nor used to train models".
- Training: Evanesca never trains on conversations. OVHcloud, Scaleway, AKI.IO and Infomaniak state that they don't either; Mistral AI lets its customers object to training, and Evanesca's account objects, except for what is sent to Mistral Large 4: it is a preview, and Mistral's commercial terms let it use the data of preview models for training, whatever the objection.
- Jurisdiction: every model runs at a European operator, under European law. The site and its relay run on Vercel (Vercel Inc., a US company) in its Paris region; nobody keeps a copy of the conversations, so a CLOUD Act order has nothing to reach. Account and billing data: a Neon database (Databricks, Inc.) in Frankfurt; e-mails: Resend; payments: Stripe Payments Europe (Ireland).
- Checks: each model's passport shows which of six checks it passed (licence, provenance, security, GDPR, benchmarks, live conversation) — and which it misses or has not had yet.
- Pricing: credit from €2, VAT included, each with its invoice; credit never expires, not even when the account is closed; the exact cost is shown under every answer. Per-model prices: https://evanesca.app/models.

## Pages
- [Home](https://evanesca.app): what Evanesca is, Agent mode, where data goes, comparison with ChatGPT, Gemini, Copilot, Claude and Meta AI, the law (GDPR, AI Act, CLOUD Act), the checks, the models, pricing, FAQ
- [Agent mode](https://evanesca.app/agent): what the agent does step by step, its tools, its spending cap, where its files and calls go
- [Web search](https://evanesca.app/web-search): how answers are searched and sourced, and what goes to Linkup
- [Image generation](https://evanesca.app/image-generation): FLUX.1 and PhotoMaker V2 in Switzerland, prices per second, rules for faces
- [Why Evanesca](https://evanesca.app/why-evanesca): the reasons to choose it, each linked to its proof

### Models and prices
- [Models run in Europe](https://evanesca.app/models): every model with maker, licence, size, operator, place, checks passed and price — all run in Europe
- [Mistral Large 4](https://evanesca.app/models/mistral-large-4): Mistral AI, —, run by Mistral AI (EU region of Mistral AI), 4/6 checks
- [DeepSeek V4.1 Flash](https://evanesca.app/models/deepseek-v4.1-flash): DeepSeek, MIT, run by AKI.IO (Germany (AKI.IO)), 6/6 checks
- [GLM-5.3](https://evanesca.app/models/glm-5.3): Zhipu / Z.ai, GLM-5.3 License, run by AKI.IO (Germany (AKI.IO)), 6/6 checks
- [Qwen3.8 27B](https://evanesca.app/models/qwen3.8-27b): Qwen, Apache-2.0, run by Scaleway (Paris, France), 6/6 checks
- [DeepSeek V4 Flash](https://evanesca.app/models/deepseek-v4-flash): DeepSeek, MIT, run by Scaleway (Paris, France), 6/6 checks
- [Apertus v1.5 70B](https://evanesca.app/models/apertus-v1.5-70b): Swiss AI Initiative, Apache-2.0, run by Infomaniak (Switzerland (Infomaniak)), 4/6 checks
- [GLM-5.2](https://evanesca.app/models/glm-5.2): Zhipu / Z.ai, MIT, run by Scaleway (Paris, France), 6/6 checks
- [Qwen3.6 35B](https://evanesca.app/models/qwen3.6-35b): Qwen, Apache-2.0, run by Scaleway (Paris, France), 6/6 checks
- [Gemma 4 26B](https://evanesca.app/models/gemma-4-26b): Google, Apache-2.0, run by AKI.IO (Germany (AKI.IO)), 6/6 checks
- [Mistral Small 4](https://evanesca.app/models/mistral-small-4-119b): Mistral AI, Apache-2.0, run by Mistral AI (EU region of Mistral AI), 5/6 checks
- [Qwen3.5 397B](https://evanesca.app/models/qwen3.5-397b): Qwen, Apache-2.0, run by Scaleway (Paris, France), 6/6 checks
- [GPT-OSS 120B](https://evanesca.app/models/gpt-oss-120b): OpenAI, Apache-2.0, run by Scaleway (Paris, France), 5/6 checks
- [Qwen3 Coder 30B](https://evanesca.app/models/qwen3-coder-30b): Qwen, Apache-2.0, run by Scaleway (Paris, France), 5/6 checks
- [Qwen3 235B](https://evanesca.app/models/qwen3-235b): Qwen, Apache-2.0, run by Scaleway (Paris, France), 5/6 checks
- [Mistral Small 3.2](https://evanesca.app/models/mistral-small-3.2): Mistral AI, Apache-2.0, run by Scaleway (Paris, France), 5/6 checks
- [Llama 3.3 70B](https://evanesca.app/models/llama-3.3-70b): Meta, Llama 3.3 Community License, run by Scaleway (Paris, France), 5/6 checks
- [Pixtral 12B](https://evanesca.app/models/pixtral-12b): Mistral AI, Apache-2.0, run by Scaleway (Paris, France), 5/6 checks
- [Compare models](https://evanesca.app/compare): models side by side — maker, size, context, tool calling, checks, price
- [Benchmarks](https://evanesca.app/benchmarks): the six checks, model by model — what each model passed and what it misses — and the makers' published scores, with sources
- [Pricing](https://evanesca.app/pricing): per-token prices of every model, credit from €2, no subscription
- [Business](https://evanesca.app/business): Evanesca for teams — DPA, sub-processors, SSO, spending limits, Agent mode caps

### Trust and law
- [Answer passport](https://evanesca.app/passport): each passport field, what the operators keep, the six checks, and what a passport does not prove
- [Sovereignty](https://evanesca.app/sovereignty): how Evanesca decides where a model runs and who can be compelled to hand data over
- [Transparency](https://evanesca.app/transparency): the six checks, how each is performed, what a missing stamp means
- [AI Act](https://evanesca.app/ai-act): what the EU AI Act asks of model makers, of Evanesca and of its users
- [Sources](https://evanesca.app/sources): dated, verbatim policy quotes from ChatGPT, Claude, Gemini, Microsoft Copilot and Meta AI, read on 2026-09-29

### Developers
- [Developer docs](https://evanesca.app/docs): guides and the API reference of the OpenAI-compatible API — listed below, under Documentation

### Company and legal
- [About](https://evanesca.app/about) · [Contact](https://evanesca.app/contact) · [Blog](https://evanesca.app/blog)
- [Legal notice](https://evanesca.app/legal): publisher, privacy of this website (no cookies, no trackers), sub-processors
- [Privacy policy](https://evanesca.app/privacy) · [Terms](https://evanesca.app/terms) · [Right of withdrawal](https://evanesca.app/withdrawal)

### Articles
- [Sovereign AI: build your own cluster, or use an API?](https://evanesca.app/blog/sovereign-ai-cluster-or-api): Palantir and NVIDIA's on-premises sovereign AI design starts at 16 servers and 32 GPUs. What owning buys, what it leaves open, and when an API is enough.
- [DeepSeek V4.1 Flash: what it is, and where it runs](https://evanesca.app/blog/deepseek-v4-1-flash): DeepSeek V4.1 Flash: a 552B multimodal MoE with a 1M context, under MIT, released on 10 September 2026. On Evanesca, AKI.IO runs it in Germany.
- [OpenRouter alternatives and competitors: what each one changes](https://evanesca.app/blog/openrouter-alternatives): OpenRouter alternatives and competitors compared on what makes teams leave: jurisdiction, data handling, fees, speed or fine-tuning. Dated and sourced.
- [French open-source AI: the companies, the models, and where they run](https://evanesca.app/blog/french-open-source-ai): Mistral AI, Hugging Face, OVHcloud, Scaleway: who does what in French open-source AI, and why a model's origin does not decide where your data goes.
- [What is open-source AI?](https://evanesca.app/blog/what-is-open-source-ai): Open-source AI lets anyone use, study, modify and share a model, with its weights, code and training-data information. What qualifies, and what it changes.
- [What is open-weight AI, and what can you do with the weights?](https://evanesca.app/blog/what-is-open-weight-ai): An open-weight model publishes its weights, the numbers it learned in training. What you get, what you don't, how much memory they need, and who can run them.
- [Open-source AI gateways and inference servers you can host yourself](https://evanesca.app/blog/self-hosted-ai-gateways): LiteLLM, vLLM, SGLang, Ollama, TGI, Xinference: what each self-hosted tool does, what running it costs, and when a managed EU API is the simpler route.
- [How to choose an AI API aggregator for your company](https://evanesca.app/blog/ai-api-aggregator-for-companies): Five questions to ask an AI API aggregator before you sign — jurisdiction, data kept, billing, catalogue, compatibility — and how five providers answer them.
- [GDPR and the CLOUD Act: why hosting your AI in the EU is not enough](https://evanesca.app/blog/gdpr-cloud-act-eu-hosting): The GDPR governs transfers; the CLOUD Act follows the company. Why an EU data centre run by a US group stays within reach, and how to check a provider.
- [Is OpenAI GDPR-compliant? What ChatGPT and the API do with your data](https://evanesca.app/blog/openai-gdpr-compliance): OpenAI offers EU contracts and transfer clauses, but it remains a US company within reach of the CLOUD Act. What that means for ChatGPT, the API and you.
- [Open-weight AI models in 2026: which to use for what, and who runs them](https://evanesca.app/blog/open-weight-models-2026): The open-weight models of 2026 — GLM, Qwen, DeepSeek, GPT-OSS, Llama, Mistral — sorted by use, with size, licence, price and the company that runs them.
- [Open-weight reasoning models: what thinking costs, and how to choose one](https://evanesca.app/blog/open-weight-reasoning-models): Reasoning models think before they answer, and that thinking is billed as output. Which open-weight models reason, what it costs, and how to choose one.
- [Tool calling on open-weight models: why it depends on who runs them](https://evanesca.app/blog/tool-calling-open-weight-models): Tool calling turns a model into an agent, but it depends on the serving stack as much as on the weights. How to check it in one call, and which models pass.
- [AI API aggregators: one key for many models, and the question of who runs them](https://evanesca.app/blog/ai-api-aggregators): An AI API aggregator puts many models behind one OpenAI-compatible key. How OpenRouter, Together AI, Groq, Fireworks AI and Evanesca differ.
- [Self-hosting an LLM or paying per token: where the break-even really is](https://evanesca.app/blog/self-hosting-llm-cost): A rented H100 costs the same whether it serves one token or a billion. The break-even against per-token prices, worked out with real October 2026 prices.
- [Embedding models for RAG: how to choose one before you index](https://evanesca.app/blog/embedding-models-for-rag): Vector size, context window and price decide which embedding model to index a RAG corpus with. The open-weight options run in France, and how to pick one.
- [European inference providers: who actually runs AI models in Europe](https://evanesca.app/blog/european-inference-providers): Who runs AI models in Europe: OVHcloud, Scaleway, Mistral AI, IONOS, STACKIT, AKI.IO, Infomaniak, Nebius and more. Company, data centres, prompts.

### Comparisons
- [Evanesca vs ChatGPT: what changes for your conversations](https://evanesca.app/vs/chatgpt): ChatGPT has OpenAI's own models and more features. Evanesca is an AI agent and chat run in Europe that keeps no copy of your chats. Both sides, sourced.
- [Evanesca vs Mistral Vibe, formerly Le Chat: two French AI chats, two ways of handling your words](https://evanesca.app/vs/mistral-vibe): Mistral Vibe, formerly Le Chat, is French and feature-rich, but keeps your chats and trains on them by default. Evanesca keeps no copy. Compared.
- [Evanesca vs Lumo by Proton: two private AI chats, one Swiss and one French](https://evanesca.app/vs/proton-lumo): Lumo, by Proton, keeps no logs and syncs an encrypted history. Evanesca, a French AI agent and chat, runs its models in Europe, paid per use. Compared.
- [Evanesca vs OpenRouter: one router for every model, or models run in Europe](https://evanesca.app/vs/openrouter): OpenRouter offers far more models, often for less. Evanesca runs its models in Europe with European operators. Price, data and law, side by side.
- [Evanesca vs OrcaRouter: a zero-markup router from Singapore, or models run in Europe](https://evanesca.app/vs/orcarouter): OrcaRouter is cheaper and far broader. Evanesca runs every model in Europe, each at a named operator. Price, prompts, region and law, side by side.
- [Evanesca vs Together AI: the same open models, other prices, other defaults](https://evanesca.app/vs/together-ai): Together AI is cheaper on most open models both serve, and fine-tunes. Evanesca runs its models in Europe and stores no prompt at all.
- [Evanesca vs Groq: raw speed, or models run in Europe](https://evanesca.app/vs/groq): Groq is built for speed and has a free plan. Evanesca runs its models in Europe and keeps no prompt. GPT-OSS prices, data and law compared.
- [Evanesca vs Fireworks AI: fine-tuning and speed tiers, or models run in Europe](https://evanesca.app/vs/fireworks-ai): Fireworks AI keeps no prompts by default and adds fine-tuning and speed tiers. Evanesca runs its models in Europe. Data, region and price compared.
- [Evanesca vs Venice AI: encrypted privacy modes, or models run in Europe](https://evanesca.app/vs/venice-ai): Venice AI offers encrypted and enclave privacy modes, often at lower prices. Evanesca runs its models in Europe with European operators. Side by side.

## Documentation
- [Build with Evanesca](https://evanesca.app/docs): The OpenAI-compatible API on AI models run in Europe: where to start.
- [Send your first request](https://evanesca.app/docs/quickstart): A key, the base URL and one call in cURL, Python or JavaScript — then streaming and the response headers.

- **Guides**
- [Create images](https://evanesca.app/docs/images): FLUX.1 [schnell] and PhotoMaker V2, run by Infomaniak in Switzerland and billed per second of generation.
- [Embeddings for search](https://evanesca.app/embeddings): Vectors for your documents, for search and RAG, billed per input token.
- [Web search](https://evanesca.app/docs/web-search): web_search and web_fetch for your agent over MCP, through Linkup, billed per call.
- [MCP server](https://evanesca.app/mcp): Connect Claude Code, Cursor or Cline with a key — ChatGPT and Claude with OAuth 2.1.
- [Integrations](https://evanesca.app/integrations): Claude Code, Cline, LiteLLM, n8n, LangChain and other coding agents, frameworks and platforms: one guide per tool.
  - [n8n](https://evanesca.app/integrations/n8n): One OpenAI credential pointed at Evanesca runs your AI Agent and embeddings nodes in Europe.
  - [Microsoft Foundry](https://evanesca.app/integrations/azure-foundry): Bring your own model: Evanesca's models in Foundry Agent Service, with the inference run in Europe.
  - [LiteLLM](https://evanesca.app/integrations/litellm): Add Evanesca to LiteLLM's SDK or proxy with the openai/ prefix: models run in Europe behind your virtual keys, budgets and spend tracking.
  - [Claude Code](https://evanesca.app/integrations/claude-code): Point Claude Code at Evanesca's Anthropic-format endpoint and run the terminal agent on open models run in Europe, tool calls included.
  - [OpenCode](https://evanesca.app/integrations/opencode): Declare Evanesca as an OpenAI-compatible provider in opencode.json and code from the terminal with open models run in Europe.
  - [Cline](https://evanesca.app/integrations/cline): Choose Cline's OpenAI Compatible provider, enter Evanesca's base URL, and the VS Code agent and its CLI run on models in Europe.
  - [Kilo Code](https://evanesca.app/integrations/kilo-code): Register Evanesca as a custom provider in kilo.jsonc: Kilo Code runs in VS Code, JetBrains or its CLI on models run in Europe.
  - [Continue](https://evanesca.app/integrations/continue): List Evanesca's models in Continue's config.yaml with provider openai and apiBase, for chat, edits and agent mode on models in Europe.
  - [Aider](https://evanesca.app/integrations/aider): Run Aider, the pair programmer of the terminal, on models run in Europe: two environment variables and the openai/ prefix.
  - [Zed](https://evanesca.app/integrations/zed): Add Evanesca as an OpenAI-compatible provider in Zed's settings.json and drive its agent panel with open models run in Europe.
  - [goose](https://evanesca.app/integrations/goose): Register Evanesca as a custom provider in goose, on the desktop or in the CLI, and run its extensions on models run in Europe.
  - [Hermes Agent](https://evanesca.app/integrations/hermes-agent): Run Nous Research's Hermes Agent on a custom endpoint: Evanesca's base URL in config.yaml, open models run in Europe behind it.
  - [OpenClaw](https://evanesca.app/integrations/openclaw): Add Evanesca as a model provider in openclaw.json and run your self-hosted OpenClaw agents on open models run in Europe.
  - [LangChain](https://evanesca.app/integrations/langchain): Point ChatOpenAI and OpenAIEmbeddings at Evanesca's base URL and build LangChain apps and agents on models run in Europe.
  - [LlamaIndex](https://evanesca.app/integrations/llamaindex): Build LlamaIndex RAG pipelines and agents on models run in Europe with OpenAILike and OpenAILikeEmbedding pointed at Evanesca.
  - [Vercel AI SDK](https://evanesca.app/integrations/vercel-ai-sdk): Create an OpenAI-compatible provider for Evanesca in the Vercel AI SDK and stream text, tools and embeddings from models in Europe.

- **Platform**
- [Authentication](https://evanesca.app/docs/authentication): sk-eva- keys sent as Bearer tokens, and the three rights of the OAuth connector.
- [Models and Europe](https://evanesca.app/docs/models-and-europe): Where every model runs, what each operator keeps, and the compliance record GET /models returns.
- [Errors](https://evanesca.app/docs/errors): The error format, every status and type, and what to retry.
- [Billing](https://evanesca.app/docs/billing): Per-token prices, images per second, web search per call, prepaid credit and invoices.

- API reference
  - [API reference](https://evanesca.app/docs/api): Every operation: parameters, examples, responses, where it runs and what it costs.

  - **Models**
  - [List models](https://evanesca.app/docs/api/list-models): GET /models
  - [Retrieve a model](https://evanesca.app/docs/api/retrieve-model): GET /models/{model}

  - **Chat**
  - [Create a chat completion](https://evanesca.app/docs/api/create-chat-completion): POST /chat/completions
  - [Create a message](https://evanesca.app/docs/api/create-message): POST /messages
  - [Count message tokens](https://evanesca.app/docs/api/count-message-tokens): POST /messages/count_tokens

  - **Embeddings**
  - [Create embeddings](https://evanesca.app/docs/api/create-embeddings): POST /embeddings

  - **Images**
  - [Create images](https://evanesca.app/docs/api/create-image): POST /images/generations
  - [Create portraits](https://evanesca.app/docs/api/create-image-edit): POST /images/edits

## When Evanesca fits
- Asking an AI about confidential material — contracts, payslips, health questions, source code, unpublished figures — without sending it to a US company.
- Teams that need processing in Europe, a data processing agreement and a sub-processor list.
- People who prefer paying per use to a monthly subscription.

## When Evanesca is not the right tool
- You need OpenAI's GPT, Anthropic's Claude or Google's Gemini: Evanesca does not offer them.
- You want your history synced across devices by the provider: Evanesca keeps it in your browser.
- You need a fully offline, local model: Evanesca runs models on French operators' servers.

## En français
- [Accueil](https://evanesca.app/fr) : Evanesca est un agent et un chat IA privés — une alternative européenne à ChatGPT. Elle fait tourner en Europe des modèles d'IA de Mistral AI, la Swiss AI Initiative, Qwen, DeepSeek, Z.ai, OpenAI, Meta et Google, cherche sur le web, rédige des documents et crée des images, et ne garde aucune trace de vos messages. Dès 2 €, sans abonnement.
- [Mode Agent](https://evanesca.app/fr/agent) · [Recherche web](https://evanesca.app/fr/recherche-web) · [Création d'images](https://evanesca.app/fr/generation-images)
- [Modèles](https://evanesca.app/fr/modeles) · [Comparer](https://evanesca.app/fr/comparer) · [Tarifs](https://evanesca.app/fr/tarifs) · [Entreprises](https://evanesca.app/fr/entreprises) · [Pourquoi Evanesca](https://evanesca.app/fr/pourquoi-evanesca)
- [Passeport de réponse](https://evanesca.app/fr/passeport) · [Souveraineté](https://evanesca.app/fr/souverainete) · [Transparence](https://evanesca.app/fr/transparence) · [AI Act](https://evanesca.app/fr/ai-act) · [Sources](https://evanesca.app/fr/sources)
- [Construire avec Evanesca](https://evanesca.app/fr/docs) · [Envoyer votre première requête](https://evanesca.app/fr/docs/demarrage-rapide) · [Créer des images](https://evanesca.app/fr/docs/images) · [Embeddings pour la recherche](https://evanesca.app/fr/embeddings) · [Recherche web](https://evanesca.app/fr/docs/recherche-web) · [Serveur MCP](https://evanesca.app/fr/mcp) · [Intégrations](https://evanesca.app/fr/integrations) · [n8n](https://evanesca.app/fr/integrations/n8n) · [Microsoft Foundry](https://evanesca.app/fr/integrations/azure-foundry) · [Authentification](https://evanesca.app/fr/docs/authentification) · [Modèles et Europe](https://evanesca.app/fr/docs/modeles-et-europe) · [Erreurs](https://evanesca.app/fr/docs/erreurs) · [Facturation](https://evanesca.app/fr/docs/facturation) · [Référence de l'API](https://evanesca.app/fr/docs/api) · [LiteLLM](https://evanesca.app/fr/integrations/litellm) · [Claude Code](https://evanesca.app/fr/integrations/claude-code) · [OpenCode](https://evanesca.app/fr/integrations/opencode) · [Cline](https://evanesca.app/fr/integrations/cline) · [Kilo Code](https://evanesca.app/fr/integrations/kilo-code) · [Continue](https://evanesca.app/fr/integrations/continue) · [Aider](https://evanesca.app/fr/integrations/aider) · [Zed](https://evanesca.app/fr/integrations/zed) · [goose](https://evanesca.app/fr/integrations/goose) · [Hermes Agent](https://evanesca.app/fr/integrations/hermes-agent) · [OpenClaw](https://evanesca.app/fr/integrations/openclaw) · [LangChain](https://evanesca.app/fr/integrations/langchain) · [LlamaIndex](https://evanesca.app/fr/integrations/llamaindex) · [Vercel AI SDK](https://evanesca.app/fr/integrations/vercel-ai-sdk)
- [À propos](https://evanesca.app/fr/a-propos) · [Contact](https://evanesca.app/fr/contact) · [Blog](https://evanesca.app/fr/blog) · [Mentions légales](https://evanesca.app/fr/mentions-legales) · [Confidentialité](https://evanesca.app/fr/confidentialite) · [Conditions](https://evanesca.app/fr/conditions) · [Rétractation](https://evanesca.app/fr/retractation)

## Optional
- [Full text](https://evanesca.app/llms-full.txt): the home page, the model list with checks and prices, the answer passport, the sources and a summary of the API, in Markdown, generated from the same data as the site