One API for all AI models. Governed.

Sovereign EU infrastructure. PII redaction. Auto-failover. Zero prompt-content retention by default. The audit trail your DPO can hand to an AI Act auditor.

AAcme EU●app.brainorchestra.ai/dashboard

Dashboard

100% EU residency · 0 policy refusals

Spend · 30d

€2,140.82

▲ 18.9%

Requests · 30d

12,447

▲ 23.4%

P50 latency

412 ms

▼ 8.2%

Active actors

▲ 4

Requests · 30d

12,447 total

Recent activity

Audit Explorer →

Time	Event	Actor	Model	Region	Detail
14:03:21	Allowed	jonatan.berg@acme.eu	claude-opus-4-7	fr-par-1	1,247 in / 512 out
14:03:20	PII redacted	jonatan.berg@acme.eu	mistral-large	fr-par-1	1 email redacted
14:03:19	Denied	agent_3vQk_summarizer	gpt-4o	—	model host outside EU
14:03:18	Allowed	agent_bot_customer_support	mistral-devstral-sweden	se-sto-1	routed via policy
14:03:17	Trace stored	anna.lind@acme.eu	claude-haiku-4-5	fr-par-1	trace t_30vPb · €0.0214

Production-ready

Per-request audit trailEU data-residency tiersOpenAI-compatible

The problem with direct LLM access

Data exposure

Sending sensitive data to LLMs without proper controls creates GDPR risk. Without governance, organizations lack visibility into what data is being shared with which providers.

No audit trail

EU AI Act (Aug 2026) introduces record-keeping requirements for AI systems. Many organizations lack structured logging of AI usage — who asked what, when, and which model answered.

No territorial control

Most LLM providers process data in the US by default. Enforcing data sovereignty per request, per team, or per use case typically requires custom infrastructure.

Capabilities

Three capabilities. One endpoint.

Intelligent Gateway

Single API endpoint for all LLM providers. Smart routing by cost, speed, quality, and territorial policy. Supports text, image, and PDF input across every compliance tier. OpenAI-compatible format — no SDK changes required.

AAcme EU●app.brainorchestra.ai/dashboard

Model health

12 models · 30d

Models · 30d

All models →

Model	P50	Success	Requests	Spend
claude-opus-4-7	187 ms	100.0%	4,218	€812.40
mistral-large	242 ms	99.7%	3,892	€586.21
claude-sonnet-4-6	204 ms	99.9%	3,107	€498.62
claude-haiku-4-5	112 ms	100.0%	2,104	€201.14
mistral-devstral-sweden	338 ms	99.0%	1,401	€331.07
gemini-pro	268 ms	99.6%	1,188	€247.55
claude-opus-4-8	196 ms	100.0%	972	€384.10
magistral-medium	311 ms	99.4%	844	€166.92
mistral-codestral	159 ms	99.8%	703	€97.41
mistral-medium	984 ms	98.4%	621	€128.00
gpt-4o	221 ms	99.5%	402	€118.73
nova-lite-sweden	297 ms	100.0%	211	€82.00

Per-Request Audit Trail

Every request logged with actor identity, model attribution, territorial proof, and cost. Searchable, exportable, designed to support compliance workflows.

AAcme EU●app.brainorchestra.ai/dashboard

Audit log

12,447 events · 30d · exportable

Audit log · 30d

Export →

Time	Event	Actor	Model	Region	Detail
14:03:21	Allowed	jonatan.berg@acme.eu	claude-opus-4-7	fr-par-1	1,247 in / 512 out
14:03:20	PII redacted	jonatan.berg@acme.eu	mistral-large	fr-par-1	1 email redacted
14:03:20	Allowed	anna.lind@acme.eu	claude-haiku-4-5	fr-par-1	routed via policy
14:03:19	Denied	agent_3vQk_summarizer	gpt-4o	—	model host outside EU
14:03:18	Allowed	agent_bot_customer_support	mistral-devstral-sweden	se-sto-1	routed via policy
14:03:17	Trace stored	anna.lind@acme.eu	claude-haiku-4-5	fr-par-1	trace t_30vPb · €0.0214
14:03:16	Allowed	jonatan.berg@acme.eu	mistral-large	fr-par-1	894 in / 301 out
14:03:15	Allowed	agent_bot_customer_support	claude-haiku-4-5	fr-par-1	routed via policy
14:03:14	Trace stored	anna.lind@acme.eu	mistral-devstral-sweden	se-sto-1	trace t_30vQa · €0.0089
14:03:12	Allowed	agent_3vQk_summarizer	claude-opus-4-7	fr-par-1	2,031 in / 740 out

EU Territorial Compliance

Four routing tiers: EU-Sweden (single-country Stockholm residency), EU-Strict (EU-owned models only), EU-Cloud (EU infrastructure), Unrestricted. Enforced per request as hard constraints, configurable per team.

AAcme EU●app.brainorchestra.ai/dashboard

Projects

4 active · €2,140.82 total

Projects · 30d

All projects →

Project	Tier	Requests	Spend	Top model
Signal Hub	EU-Cloud	5,621	€1,084.20	claude-opus-4-7
Lighthouse	EU-Cloud	3,108	€527.36	mistral-large
Atelier	EU-Sweden	2,807	€389.14	mistral-devstral-sweden
Outpost	EU-Cloud	911	€140.12	claude-haiku-4-5

The platform

Everything between your application and the model layer.

One inline gateway resolves the right model, enforces your policy, emits an immutable audit record, and forwards the request to a provider on infrastructure that satisfies your contract.

One request, routed by your cost, speed and quality priorities.

Routes each request to a suitable model by your cost, speed and quality preferences, while hard-enforcing your residency tier.

Cost-, latency- and availability-weighted selection — within your compliance tier.
Per-team default tiers, per-request overrides
Text, image and PDF input across every compliance tier
Hard territorial constraints enforced before egress

Resolving model · live

policy: eu_cloud

Your app

Claims pipelinets

Support agentpy

Brain Orchestra

Resolve + route

policy → cost → latency

Providers (EU)

Bedrockeu-cen

Mistralfr-par-1

Azurese-nor

Last decision: claims-pipeline → claude-sonnet-4.6 via Bedrock eu-central-1 — chosen for capability within the eu_cloud constraint.

Every call is signed evidence by the time it returns.

Every request logged with actor identity, model attribution, territorial proof, and cost. Searchable, exportable, designed to support compliance workflows.

Actor identity on every request (customer-asserted)
Model, region and territorial tier recorded per call
Token counts and EUR cost on every span
Searchable, exportable audit log

trace · contract-review-v3

t_7Hj3v4QkR2 · 14:32 UTC

▾plan_review claude-opus-4.6€0.0421,420ms

├extract_clauses magistral-medium€0.008612ms

├classify_risk claude-haiku-4.5€0.003240ms

├draft_redline claude-sonnet-4.6€0.0221,840ms

└summarise magistral-small€0.005410ms

5 spans · depth 2

€0.080 / €0.25

Two lines of code. Your stack doesn’t notice.

Change api.openai.com to api.brainorchestra.ai and add an actor token. Your existing OpenAI SDK code keeps working — every request is tracked automatically.

Drop-in OpenAI Chat Completions schema
Python, TypeScript, Java, Go, Ruby — same patch
Bring your own provider keys, or use ours
Audit log fills within seconds of first call

OpenAI-compatible

app/llm.py

# your existing openai client — change two lines
from openai import OpenAI

client = OpenAI(
    api_key="bo_live_…",
    base_url="https://api.brainorchestra.ai/v1",
    default_headers={"X-Actor-Token": "bo_actor_…"},
)

resp = client.chat.completions.create(
    model="eu-strict",  # or a specific id
    messages=[{"role": "user", "content": "Summarize this contract"}],
)

Integration

Integrate in 5 minutes

Sign up

Create your account and set your territorial policy. Choose EU-Strict, EU-Cloud, or Unrestricted as your default.

Swap your API URL

Change api.openai.com to api.brainorchestra.ai

Every request is tracked

Audit trails, territorial routing, cost tracking — automatic for every request through the gateway.

app/llm.py

from openai import OpenAI

client = OpenAI(
    api_key="$BO_API_KEY",
    base_url="https://api.brainorchestra.ai/v1",
    default_headers={"X-Actor-Token": "bo_actor_YOUR_ACTOR_TOKEN"},
)

Model catalog

Every major LLM. One endpoint.

Chat models from Mistral, Anthropic, OpenAI, Amazon, Google and more — every provider reachable through the same OpenAI-compatible endpoint, each routed within the tiers it can serve.

Mistral

8 models

EUEU-owned · all tiers

Evroc

7 models

EUEU-owned · all tiers

Anthropic

12 models

EUEU-Cloud

OpenAI

12 models

EUEU-Cloud

berget

7 models

EUEU-Cloud + Sweden

Amazon

1 model

EUEU-Cloud + Sweden

Nebius

6 models

Unrestricted only

xAI

5 models

Unrestricted only

Google

4 models

Unrestricted only

Z.ai

1 model

Unrestricted only

View all models →

Compliance routing

Compliance routing built in

Eu_strict

EU-Strict

EU-owned models, EU infra

EU-owned models on EU infrastructure. Maximum sovereignty.

Mistral only

Eu_cloud

EU-Cloud

Any model, EU inference

Claude + Mistral + Cohere + Amazon Nova on EU infrastructure via AWS Bedrock (Frankfurt or Stockholm).

ClaudeMistral

Unrestricted

Native providers, all regions

All models, all providers. Maximum capability.

All providers

Routing shorthand

routing

"model": "eu-strict"         # Best EU-owned model
"model": "eu-strict:small"   # Cheapest EU model
"model": "auto"              # Best for your tier
"model": "mistral-large"     # Specific model

Brain Orchestra provides technical controls and structured evidence. It does not grant compliance — your legal team makes that determination.

Pricing

Simple, transparent pricing

5% platform fee on token usage through managed keys. Prepaid credit balance with transparent per-request billing. Bring your own keys to skip the platform fee entirely.

Trial

Free30 days

Full access to every feature. BYOK is completely free. BO-managed keys: pay only for tokens used + 5% convenience fee.

All features unlocked
Unlimited projects and users
BYOK: no charge at all
BO-managed: provider cost + 5%
Card required at signup

Join waitlist

ProMost popular

€79/month

Subscription tier plus 5% on managed-key tokens. Prepaid credit balance, transparent per-request billing. BYOK skips the 5% fee entirely.

Everything in Trial
100,000 requests / month
All EU-sovereignty tiers (eu_strict, eu_cloud, eu_sweden)
Mixed key model (BYOK + BO-managed)
BO-managed: provider cost + 5%
BYOK: zero per-token fee

Join waitlist

Enterprise

Customannual

Custom contracts, SLA, dedicated support. Negotiable convenience fee. Advanced identity and deployment options available on the roadmap — contact sales for current availability.

Everything in Pro
Unlimited requests
Custom convenience fee
SLA + dedicated support
SSO/SAML (roadmap — ask sales)
VPC / on-premise (roadmap — ask sales)

Contact Sales

Also available in USD ($79/mo) and SEK (899 kr/mo). Currency selected at signup. All prices exclude VAT where applicable.

In pilot

Built for agentic AI

When AI agents call AI agents, you need governance at every step. Brain Orchestra’s trace system gives you operation-level budgets, depth limits, kill switches, and a full span tree for every agent workflow.

Orchestrator agentroot span

Governance layerBrain OrchestraEvery agent-to-agent call passes through trace & control

Research agentchild agent

Writer agentchild agent

Tool callfunction

BudgetPer-operation spend limits with automatic cutoff
Depth & fan-outCap agent-to-agent nesting and parallel calls
Kill switchTerminate any running workflow instantly

Dashboard

The problem with direct LLM access

Data exposure

No audit trail

No territorial control

Three capabilities. One endpoint.

Intelligent Gateway

Model health

Per-Request Audit Trail

Audit log

EU Territorial Compliance

Projects

Everything between your application and the model layer.

One request, routed by your cost, speed and quality priorities.

Your app

Providers (EU)

Every call is signed evidence by the time it returns.

Two lines of code. Your stack doesn’t notice.

Integrate in 5 minutes

Sign up

Swap your API URL

Every request is tracked

Every major LLM. One endpoint.

Compliance routing built in

EU-Strict

EU-Cloud

Unrestricted

Routing shorthand

Simple, transparent pricing

Built for agentic AI

Get the audit trail your DPO has been asking for.