Models and API
One OpenAI-compatible API for 100+ models across cloud providers and on-prem model servers, covering chat, embeddings, images, audio, rerank, batch and files.
Models and API
One API, every model
Developers write to one OpenAI-compatible API. The gateway translates each request to the provider or model server behind it, so switching models is a configuration change, not a code change.
Self-hosted model servers on your own GPUs, NVIDIA AI Enterprise models and approved cloud providers all appear behind the same endpoints.
Model sources
Cloud and on-prem behind one endpoint
On-prem model servers
Self-hosted model servers running on your GPUs, including the Comptech AI Platform.
NVIDIA accelerated AI
NVIDIA AI Enterprise models served on your own infrastructure.
Cloud providers
Major cloud model providers, used only where your policies allow.
Your fine-tuned models
Models you have trained or tuned yourself, published behind the same API.
Endpoints
Every type of AI request
Chat and completions
Chat, text completions, streaming and function calling.
Embeddings
Embeddings for search and RAG from any supported model.
Images
Image generation and editing endpoints.
Audio
Speech-to-text and text-to-speech endpoints.
Rerank
Reranking for retrieval pipelines.
Batch and files
Batch jobs and file uploads for large offline workloads.
Model management
Models as a managed catalogue
Model aliases
Applications call a stable name, such as "bank-chat", while you change the model behind it.
Model catalogue
One list of approved models, with their providers, limits and costs.
Per-model settings
Default parameters, context limits and timeouts per model.
Endpoints
What the API supports
Chat and completions
- Typical use
- Assistants, agents, summarisation
- Model sources
- On-prem and cloud
Embeddings
- Typical use
- Search and RAG
- Model sources
- On-prem and cloud
Images
- Typical use
- Generation and editing
- Model sources
- On-prem and cloud
Audio
- Typical use
- Transcription and speech
- Model sources
- On-prem and cloud
Rerank
- Typical use
- Retrieval quality
- Model sources
- On-prem and cloud
Batch and files
- Typical use
- Large offline jobs
- Model sources
- Providers that support batch
Included
With every Comptech product
On premises or air-gapped
Runs in your own data centre, so prompts and responses stay under your control.
Single sign-on
SAML and OIDC sign-in, with AD/LDAP groups mapped to teams and roles.
Secrets vault
Provider credentials held centrally, never handed to applications.
DC/DR design
Designed for a primary data centre and a disaster recovery site.
Local support
Comptech engineers in Bangladesh for deployment and support.
Pilot and training
A focused pilot on one use case, plus training for platform and application teams.
Explore
Other Comptech products
Comptech Container Platform
Enterprise Kubernetes with GitOps, a private registry and DC/DR.
Comptech AI Platform
Private generative AI and MLOps on your own GPUs.
Comptech Data Pipeline
Open lakehouse with SQL, pipelines, dashboards and lineage.
Comptech DocuVault
Document management for banks: capture, document AI, workflows and records.
Comptech AIOps
Monitoring, service desk, AI root cause and DR assurance for bank infrastructure.
Comptech VisionVault
On-prem AI video intelligence, transcription and evidence management.
Comptech SecOps
Security for every workload across your Comptech platforms.
Request a pilot
Tell us which applications and models you want to bring under control first. We'll plan an AI Gateway pilot around them.
Related services