DrexDrex Router
Drex Router
A small model that picks the right LLM or SLM and reasoning effort for every step your agent takes. Your agent makes the call.
expense-agent, step 2: 15% of €240. Drex Router picks Ministral 3B, no reasoning.
Agent call
POST /v1/route { "agent": "expense-agent", "step": 2, "task": "15% of €240" }
- 57–87 ms
- per routing decision
- 1/28
- the cost of Jev Router at near-equal quality
- 87.6%
- on MMLU at $0.10 per 1,000 questions
Three questions, three models
What’s 15% of €240?
GPT-6 LunaNo reasoning$0.001Is Lisbon rainy in March?
Claude Sonnet 5.5Low effort$0.003Plan 5 days in Lisbon for two, under €1,500.
Claude Opus 5.5High effort$0.050
−32%model spend vs Claude Opus 5.5 on every turn
- Routed
- $0.054
- All Opus
- $0.080
Illustrative model spend in USD. All Opus uses Claude Opus 5.5 for every turn.
Route to any model
17 models are built in. Route to anything else by sending its price, context window and tags. No retraining.
Large
- Claude Opus 5.5
- Claude Sonnet 5.5
- GPT-6 Sol
- GPT-4 1106 preview
Fast
- GPT-6 Luna
- Gemini 3.8 Flash
- Claude Haiku 5.5
- DeepSeek V4.1 Flash
- GLM 5.3 Flash
- GPT-4o mini
Open weights
- gpt-oss-120b
- Gemma 4 31B
- Llama 3.1 8B
- Mistral Small 3.2 24B
- Mistral Small
- Mixtral 8x7B
- Ministral 3B
Your profiles
- Qwen
- Flint by Recursive
- Your fine-tune
Same quality, a fraction of the cost
Answer quality vs cost
MMLU accuracy vs cost
One call before every turn
- 01
Send the turn · Messages and up to 255 candidates, at every step
- 02
Get a decision · The pick and a probability for every candidate
- 03
Call the model · With your own keys or gateway
POST /v1/route
{
"messages": [
{ "role": "system",
"content": "You are trip-agent. Step 1: plan the itinerary." },
{ "role": "user",
"content": "Plan 5 days in Lisbon, under €1,500" }
],
"candidates": [
"openai/gpt-6-luna",
"anthropic/claude-sonnet-5.5",
"anthropic/claude-opus-5.5",
{ "id": "flint", "provider": "self-hosted",
"price_in": 0.1, "price_out": 0.4,
"context": 262144, "tags": ["coding", "small"] }
],
"cost_weight": 0.3
}{
"selected": "anthropic/claude-opus-5.5",
"probabilities": {
"anthropic/claude-opus-5.5": 0.81,
"anthropic/claude-sonnet-5.5": 0.15,
"openai/gpt-6-luna": 0.03,
"flint": 0.01
},
"request_id": "req_8f2c…"
}Frequently asked questions
Does Drex Router proxy my requests?
No. It returns a decision. Your code calls the selected model with your own keys, directly or through your gateway or LiteLLM.
What model is it built on?
A 12B Gemma-based Nace decision model. It reads conversations of up to 32,768 tokens.
What happens if routing fails?
The API returns an error and no pick: 504 on a timeout, 503 if routing is unavailable. You aren’t charged, and your agent calls its default model.
Can I tune it on my own traffic?
Yes. Talk to us about tuning Drex Router on turns from your agent.

Route a turn from your own agent
See which model Drex Router picks for your next turn.
