Model Configuration

The Right Model
for Every Job.

Not every task needs Claude Opus. Not every task can use GPT-4o mini. EnGenAI gives you granular control over which model each agent uses — per agent, per task type, per organization plan.

The One-Model Problem

Most platforms pick one model for everything. That's wrong in two directions at once.

The Expensive Problem

Using Opus 4.6 for every task — including updating a comment in a doc file, writing a changelog entry, or running a code review on 5 lines of CSS. You're paying premium prices for zero-value premium reasoning.

Opus for documentation = $0.15/task instead of $0.002/task
The Cheap Problem

Using Haiku or GPT-4o mini for everything — including architecture decisions, security review, and designing database schemas. You get fast, cheap answers that are subtly wrong in ways that cost you weeks to fix.

Haiku for architecture = fast wrong answers

The solution isn't one model. It's the right model for each task — automatically.

Per-Agent Model Assignment

Assign primary and fallback models to each agent based on their role. Keith gets Opus for architecture thinking. Sage gets Gemini 2.5 Pro for documentation.

Per-Agent Model Assignment
primary + fallback
K
Keith
CPO
claude-opus-4-6 fallback gpt-4o
Architecture · Specs
P
PROMI
Orchestrator
claude-sonnet-4-6 fallback claude-haiku-4-5
Orchestration
S
Sophi
Backend
claude-opus-4-6 fallback claude-sonnet-4-6
Backend · DB
M
Marv
Frontend
claude-sonnet-4-6 fallback gpt-4o-mini
Frontend · UI
Sg
Sage
Knowledge
gemini-2.5-pro fallback claude-haiku-4-5
Docs · Research
Per-Task-Type Override
overrides agent assignment
architecture claude-opus-4-6
coding claude-sonnet-4-6
documentation gemini-2.5-pro
research gemini-2.5-pro
review claude-sonnet-4-6

Task-type overrides apply regardless of which agent is assigned. Architecture tasks always use Opus 4.6.

Task-Type Routing

Go deeper: assign by task type, not just agent. All architecture decisions → Opus 4.6. All documentation → Gemini 2.5 Pro. All code review → Sonnet 4.6.

Task-type assignments override per-agent assignments. If you set "architecture → Opus 4.6", every architecture task uses Opus regardless of which agent is assigned to it.

Task types are inferred from the task context, agent role, and PREVC phase. No manual tagging required — the routing engine classifies automatically.

Priority order: task-type override → agent assignment → org default → platform default. Every task always has a valid model target.

Model Groups by Plan

Plan tiers gate model access. Starter orgs use efficient models. Enterprise orgs unlock premium models and can bring their own keys.

Model Group Models Included Min Plan
Starter
claude-haiku-4-5 gpt-4o-mini gemini-flash
Starter min tier
Professional
+ Starter group claude-sonnet-4-6 gpt-4o gemini-2.5-pro
Pro min tier
Enterprise
+ Pro group claude-opus-4-6 custom fine-tuned
Enterprise custom pricing

Model groups are enforced per-organization at the platform level. A Starter organization cannot use Opus 4.6 — even if they configure it manually in their agent settings. Plan gating happens before the routing layer.

BYOK — Enterprise Only
Enterprise

Enterprise organizations can bring their own API keys for any supported LLM provider. BYOK bypasses EnGenAI's model groups entirely — use any model available on your provider account, including custom fine-tuned models and preview APIs.

Cost Optimization

Route routine tasks to efficient models. Reserve premium models for what they're worth.

Efficient Models For
  • Documentation updates
  • Code review on style/formatting
  • Test writing (unit tests)
  • Changelog and commit messages
  • UI component scaffolding
Premium Models For
  • Architecture decisions
  • Security design review
  • Novel problem solving
  • Database schema design
  • Complex multi-service reasoning
65%
cost reduction achievable with smart routing

Bring Your Own API Keys

Pro and Enterprise organisations can connect their own provider API keys. Use your negotiated rates, your own rate limits, and your existing provider relationships — while keeping EnGenAI's routing, monitoring, and failover.

Your Keys

Store your OpenAI, Anthropic, or Google API keys. Encrypted in GCP Secret Manager — never in the database.

Auto-Discovery

When you add a key, EnGenAI probes the provider to discover which models you have access to. No manual config needed.

Lower Cost

BYO key requests bypass EnGenAI's LLM markup. You pay your provider directly at your negotiated rate.

External subscriptions — Connect your existing Claude Desktop, ChatGPT, or Google AI subscriptions. EnGenAI detects available capabilities via JSONB auto-discovery and routes accordingly.

Per-agent
primary + fallback model control
Per-task-type
routing override by work category
65% cost
reduction possible with smart routing

Next: Intelligent LLM Routing

Model assignment is the what. LLM routing is the how — health monitoring, fallback chains, and real-time rate limiting.