- 🇫🇷 France·Mistral AI
Model Catalog
Every model below is reachable through the same OpenAI-compatible endpoint. For each model, you see in which jurisdictions it can run and which provider serves it — your policy decides which lane is taken per request.
Frontier chat
Flagship multimodal models for the hardest workloads.
12 models
Frontier chat
Flagship multimodal models for the hardest workloads.
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇩🇪 Germany·IONOS
- 🇫🇷 France·Scaleway
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·STACKIT
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Stockholm + 🇪🇺 EU·AWS Bedrock
- 🇸🇪 Stockholm + 🇪🇺 EU·AWS Bedrock
- 🇺🇸 United States·Google AI
Workhorse chat
Production-grade general-purpose models at mid-size.
21 models
Workhorse chat
Production-grade general-purpose models at mid-size.
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius(fast lane)
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇩🇪 Germany·STACKIT
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇩🇪 Germany·STACKIT(131K context)
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·STACKIT(37K context)
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Stockholm + 🇪🇺 EU·AWS Bedrock
- 🇸🇪 Stockholm + 🇪🇺 EU·AWS Bedrock
- 🇺🇸 United States·Google AI
- 🇺🇸 United States·Google AI
Reasoning
Thinking-style models for multi-step problem solving.
7 models
Reasoning
Thinking-style models for multi-step problem solving.
- 🇫🇷 France·Mistral AI
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius(fast lane)
- 🇫🇷 France·Scaleway
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇸🇪 Sweden Central·Azure OpenAI
- 🇸🇪 Sweden Central·Azure OpenAI
Code & developer
Code completion, FIM, and agentic coding.
5 models
Code & developer
Code completion, FIM, and agentic coding.
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
Vision & multimodal
Image-in models where vision is the primary capability.
4 models
Vision & multimodal
Image-in models where vision is the primary capability.
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇫🇷 France·Scaleway
Compact & edge
Small open-weight models for high-throughput / low-latency tasks.
6 models
Compact & edge
Small open-weight models for high-throughput / low-latency tasks.
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇩🇪 Germany·STACKIT
- 🇺🇸 United States·Google AI
Embeddings
Vector embeddings for retrieval, classification and search.
9 models
Embeddings
Vector embeddings for retrieval, classification and search.
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Mistral AI
- 🇳🇱 NL · 🇫🇮 + 🇫🇷 inference·Nebius(8K context)
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·STACKIT
- 🇩🇪 Germany·STACKIT
- 🇫🇷 France·Scaleway
- 🇩🇪 Germany·IONOS
- 🇩🇪 Germany·IONOS
- 🇩🇪 Germany·IONOS
Document & OCR
Layout-aware document parsing and optical character recognition.
2 models
Document & OCR
Layout-aware document parsing and optical character recognition.
- 🇫🇷 France·Mistral AI
- 🇩🇪 Germany·IONOS
Speech
Speech-to-text and text-to-speech.
3 models
Speech
Speech-to-text and text-to-speech.
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway(24B · 32K context)
- 🇫🇷 France·Mistral AI
- 🇫🇷 France·Scaleway
Image generation
Text-to-image inference.
1 model
Image generation
Text-to-image inference.
- 🇩🇪 Germany·IONOS
Per-token pricing, batch discounts, dedicated-endpoint options and DPA status per provider available on request. Catalogue refreshed monthly against each provider's public price list.
Request full price bookProvider Network
We aggregate LLM providers across the full spectrum behind a single endpoint. Every tier is accessible via the same API — TechVera routes to the right one based on your policy.
Providers operating exclusively under EU jurisdiction — no US parent company, no Cloud Act exposure.
US hyperscalers in EU regions — opt-in only, with explicit CLOUD-Act labelling on every response.
Direct US / international providers. Available with explicit customer opt-in for non-sensitive workloads.
You operate LLM infrastructure in the EU?
We're actively onboarding sovereign and EU-hosted inference providers.
Become a provider partner