Skip to content
BidLayersBidLayers | controlled bid operations
Models & tokens

Your models. Your keys. Your data boundary.

Run BidLayers on Claude, GPT, Gemini, Mistral, Llama or your own hosted endpoint. Bring your own API keys and pay your provider directly. Route each skill to the most economical model that meets its confidence threshold, and keep the option to switch as the market moves.

Supported providers

A neutral layer over the models you already trust.

Anthropic Claude
Direct or via Bedrock
OpenAI
Direct or via Azure
Google Gemini
Vertex AI or direct
Mistral
Direct or self-hosted
Meta Llama
Self-hosted or Bedrock
Azure OpenAI
Enterprise agreements
AWS Bedrock
Shared foundation models
Self-hosted
vLLM, TGI, Ollama
Routing

Right model for the job. Every job.

Each skill declares the capability class it needs. BidLayers picks the cheapest model in that class that clears the skill's confidence threshold, and records the choice.

Skill class
Model tier
Cost
Deterministic extraction
Small · fast · cheap
Narrative drafting
Mid · balanced
€€
Contract clause reasoning
Large · high recall
€€€
Committee memo synthesis
Large · high recall
€€€
Data boundary

Your tender text never leaves your model contract.

BidLayers is the orchestration layer, not the model provider. Prompts and responses transit directly between your tenant and the model endpoint under your own contractual terms, GDPR, DPA, data residency, retention, all yours.

Cost visibility

Every skill run, every token, accounted for.

Per-tender, per-skill and per-provider spend, exportable to your FP&A stack. Set caps and alerting per workspace. No surprise invoices.

See pricing →