An OpenAI-compatible API based on the best open-source models, hosted in our data centers in Spain. Change one line of code, start calling, and pay only for the tokens you use. No GPUs to manage, no startups to wait for, no data leaving the EU.
If you already use the OpenAI API, just change the base URL and key. Everything else stays the same. from openai import OpenAI
client = OpenAI(
base_url="https://api.todoencloud.com/v1",
api_key="TU_API_KEY",
)
resp = client.chat.completions.create(
model="[modelo-open-source]",
messages=[{"role": ";user", "content": "Hola"}],
)
We serve a selection of reference open-source models (Llama, Mistral, Qwen, DeepSeek, gpt-oss families, embeddings, and multimodal). Price per million tokens, input and output:
| Model | Input [€/Mtoken] | Output [€/Mtoken] | Best for |
|---|---|---|---|
| Lightweight or specialized models Ej.: Mistral Small, qwen3 | 0,22 € | 0,50 € | Sorting, extraction, high volume |
| General-purpose or medium-task models Ej.: Gemma 4 / Llama | 0,44 € | 1,10 € | Chat, RAG, attendees |
| Border or High-Capacity Models Ej.: gpt / glm / Deepseek | 1,45 € | 5,90 € | Reasoning, complex tasks |
| Embeddings | 0,17 € | No cost | Semantic search, RAG |
Honest advice: You almost never need the largest model. We help you choose the smallest one that solves your task— and it’s also the cheapest.
We do not read, store, reuse, or analyze your prompts or generated responses. Your product does not feed anyone else. And all processing happens in our three owned data centers in Spain, with certifications ISO 27001, 27017, 27701, and ENS.
Chatbots and assistants integrated into your product or website.
RAG over your documentation and internal sources.
Text extraction and classification at scale.
Prototypes you validate today and take to production without rewriting anything.
Start by paying per token while you validate the idea. When volume grows or you need guaranteed latency, custom guardrails, or access governance, move to a dedicated endpoint with the same API. No need to rewrite your integration: Just switch plans.
Yes. You use the official SDKs and frameworks like LangChain or LlamaIndex by only changing the base URL and key. Migration takes minutes.
Per million input and output tokens, depending on the model. No reserved capacity or fixed bill.
A selection of reference open-source models, plus embeddings and multimodal models. We publish the list and prices in the table above.
No. They are not read, stored, reused, or analyzed.
In our owned data centers in Spain, under EU legislation.
That’s where the dedicated endpoint comes in: Your own platform with guardrails, access governance, and isolated capacity, all with the same API.
Change one line, make your first call, and pay only for what you use.
“Since we delegated management of our Office 365 and all our cloud platforms to Todo En Cloud, we’ve been able to focus on our core business while feeling like we’re in the hands of professionals with in-depth knowledge of Azure and cloud platforms in general. Their proactivity and professionalism help us get the most out of all these types of platforms.”
“Since implementing the new architecture in Azure with their help, we’ve experienced a significant improvement in workload management. The scalability and robustness they offer have allowed us to handle periods of high demand with complete confidence, a key aspect for our online campus. Their DevOps service and ongoing support have been and continue to be key to our success, and this undoubtedly represents an invaluable added value.”
“The cloud resource rental service is excellent. What really makes the difference is their support team: agile, responsive, and always willing to help. We especially value having a team that understands our challenges and supports us quickly, clearly, and closely every step of the way.”
“For our data center expansion project, we needed a trusted partner to support us throughout the administrative and technical processes. We found that in TodoenCloud: we experienced close attention and excellent service, contributing ideas, building bridges, and making tasks easier. Our systems are now ready to guarantee the continuity of our business and the service we offer our clients. It’s a pleasure to work with such a professional and friendly team.”
“Todo en Cloud is an excellent option for those seeking quality and reliable cloud services. Their team has always been there to support us every step of the way, providing friendly and professional support. What we value most is their flexibility in adapting to our needs; they are always willing to listen and find tailored solutions. Thanks to their help, we have been able to optimize our resources and navigate changes more easily.”
“Working with Todo En Cloud on our migration to the AWS cloud has been an exceptional experience. From the very beginning, their team demonstrated a deep understanding of cloud architecture definition and SysOps support, being involved in every phase of the project. Todo En Cloud’s closeness and commitment provided great peace of mind, which was essential during the development and production run. Thanks to their experience, we received support on various migration projects and changes to our cloud environment, which has improved our efficiency and scalability. I would definitely recommend Todo En Cloud to any company looking for a trusted partner on their journey to the cloud.”
