Drex Max is the #1 decision model on Artificial Analysis.
Nace.AI

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"
}
Drex Router61 ms
  • Llama 3.1 8BMeta · open weights
  • GPT-6 LunaOpenAI
  • Ministral 3BMistral · open weights
    No reasoning
  • Gemini 3.8 FlashGoogle
  • Claude Haiku 5.5Anthropic
  • Claude Sonnet 5.5Anthropic
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

  1. What’s 15% of €240?

    GPT-6 LunaNo reasoning$0.001
  2. Is Lisbon rainy in March?

    Claude Sonnet 5.5Low effort$0.003
  3. Plan 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.

Drex Router
  • 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

8.58.68.78.88.99$0.1$1$10Cost per 1,000 prompts (log)Judge score (0–10)28x lower costDrex Router: 8.80 at $0.28Drex Router8.80 at $0.28Jev Router: 8.84 at $7.80Jev Router8.84 at $7.80Jev 1.14: 8.65 at $2.37Jev 1.148.65 at $2.37
306 prompts from the 2026 development sample. Log cost axis.

MMLU accuracy vs cost

7075808590$0.1$1Cost per 1,000 questions (log)Accuracy (%)11x lower costDrex Router: 87.6% at $0.10Drex Router87.6% at $0.10Jev Router: 86.4% at $1.09Jev Router86.4% at $1.0912B base: 74.1% at $0.3312B base74.1% at $0.33
1,400 MMLU questions, answered end to end. Log cost axis.

One call before every turn

  1. 01

    Send the turn · Messages and up to 255 candidates, at every step

  2. 02

    Get a decision · The pick and a probability for every candidate

  3. 03

    Call the model · With your own keys or gateway

Request
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
}
Response
{
  "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.