# Co-Location

> Co location places trading servers inside or beside an exchange's data centre to cut latency. Learn how it works, what it costs, fairness rules and who needs it.

Source: https://learn.tradelabsai.com/infrastructure/co-location/  
Track: Trading Infrastructure · Level: Advanced · Updated: 2026-10-03  
Publisher: TradeLabs AI (https://tradelabsai.com). Education, not financial advice.  
Cite as: TradeLabs Learn, "Co-Location", https://learn.tradelabsai.com/infrastructure/co-location/

Co location means placing your trading servers in the same data centre as an exchange's matching engine. Instead of data and orders crossing cities or continents, they travel a few dozen metres of cable. Co location cuts network latency from milliseconds to microseconds, which is essential for high frequency trading, market making and latency arbitrage. Exchanges sell co location as a service, alongside direct data feeds and cross connects, and it has become a significant source of exchange revenue.

## How co location works

1. **Rent space** in the exchange's data centre: a rack, part of a rack or a cage.
2. **Install your servers** and network equipment.
3. **Order cross connects:** physical cables to the exchange's order entry and market data networks.
4. **Subscribe to direct feeds** and order entry sessions.
5. **Tune hardware and software** to use the short path fully. See [Kernel Bypass and Low-Latency Networking](https://learn.tradelabsai.com/infrastructure/kernel-bypass/) and [FPGAs and Hardware Acceleration](https://learn.tradelabsai.com/infrastructure/fpgas-and-hardware-acceleration/).

## Major co location sites

| Venue | Data centre location (approx.) |
|---|---|
| CME Group | Aurora, Illinois |
| NYSE | Mahwah, New Jersey |
| Nasdaq | Carteret, New Jersey |
| Cboe US equities | Secaucus, New Jersey |
| London Stock Exchange | London area |
| Deutsche Börse (Eurex, Xetra) | Frankfurt area |

Firms often co locate at several sites and link them with fibre and microwave networks for cross venue strategies. See [Networking for Traders](https://learn.tradelabsai.com/infrastructure/networking-for-traders/).

## Fairness and equal cable lengths

Exchanges aim to treat co located customers equally. Some cut every customer's cable to the same length, coiling extra cable for racks that sit closer, so no one gains a few nanoseconds from rack position. Regulators expect co location services to be offered on fair, transparent and non discriminatory terms.

**Example: Why metres matter**
Light in fibre travels about 200 metres per microsecond, so every 100 metres of cable adds about half a microsecond one way. In a race where two firms react to the same price change, the one whose order arrives first at the matching engine gets the fill. If competing systems react within a microsecond of each other, cable length differences of 100 metres could decide the outcome. Equalised cables remove that variable, leaving the race to hardware and software speed. See [Latency in Trading](https://learn.tradelabsai.com/orders/latency-in-trading/).

## Costs

| Item | Nature of cost |
|---|---|
| Rack space and power | Monthly fees per rack or kilowatt |
| Cross connects | Monthly fee per connection |
| Market data | Direct feed fees and licences. See [Market Data Fees](https://learn.tradelabsai.com/orders/market-data-fees/) |
| Order entry sessions | Per session or port fees |
| Hardware | Servers, switches, specialised network cards |
| Staff | Engineers to manage and tune everything |

Totals range from thousands to many thousands of dollars per month per venue for a modest presence, and far more for large firms.

## Who needs co location

| Strategy | Needs co location? |
|---|---|
| Market making in liquid products | Usually yes. See [Market Making](https://learn.tradelabsai.com/strategies/market-making/) |
| Latency arbitrage | Yes |
| Short term statistical arbitrage | Often |
| Intraday strategies on minute bars | No |
| Swing and position trading | No |

## Proximity hosting

Not every firm needs space inside the exchange's own hall. Proximity hosting in nearby data centres, or cloud regions near the venue for crypto exchanges, gives much of the benefit at lower cost. For retail traders, a server in the same city or cloud region as the broker or exchange is the practical equivalent. See [VPS, Cloud and Bare-Metal Servers](https://learn.tradelabsai.com/infrastructure/vps-cloud-and-bare-metal-servers/).

## Debates

Critics argue co location gives paying firms an unfair head start over other investors. Supporters argue it is available to anyone willing to pay, improves liquidity and narrows spreads. Some venues have introduced speed bumps to blunt latency advantages. See [High-Frequency Trading](https://learn.tradelabsai.com/algo-trading/high-frequency-trading/).

## Frequently asked questions

### What is co location in trading?

Placing trading servers in an exchange's data centre, connected by short cables to its matching engine and data feeds, to minimise latency.

### How much does co location cost?

It varies by venue and setup, typically thousands of dollars per month or more once space, power, cross connects, data and hardware are included.

### Do retail traders need co location?

No. Retail strategies rarely depend on microseconds; a server in the same region as the broker or exchange is enough.

Next, learn how firms skip the operating system to save time in [Kernel Bypass and Low-Latency Networking](https://learn.tradelabsai.com/infrastructure/kernel-bypass/).

## Continue learning

- Next lesson: [Kernel Bypass and Low-Latency Networking](https://learn.tradelabsai.com/infrastructure/kernel-bypass/)
- Previous lesson: [Fault Tolerance, High Availability and Redundancy](https://learn.tradelabsai.com/infrastructure/high-availability/)
- Related: [Fault Tolerance, High Availability and Redundancy](https://learn.tradelabsai.com/infrastructure/high-availability/): High availability keeps trading systems running through hardware, network and software failures. Learn redundancy, failover, avoiding split brain and testing it.
- Related: [Latency in Trading](https://learn.tradelabsai.com/orders/latency-in-trading/): Latency is the delay between a market event and your reaction to it. Learn the sources of trading latency, how it is measured and when it matters for your trades.
- Related: [High-Frequency Trading](https://learn.tradelabsai.com/algo-trading/high-frequency-trading/): High frequency trading uses extreme speed to trade huge volumes for tiny profits per trade. Learn the main HFT strategies, the technology and the criticisms.
- Related: [Networking for Traders](https://learn.tradelabsai.com/infrastructure/networking-for-traders/): The networking basics behind trading: latency and distance, TCP versus UDP, multicast market data, packet loss, jitter and practical ways to improve connectivity.
- Related: [Kernel Bypass and Low-Latency Networking](https://learn.tradelabsai.com/infrastructure/kernel-bypass/): Kernel bypass lets trading software read network packets straight from the network card, skipping the operating system. Learn how it works and the trade offs.
- Related: [VPS, Cloud and Bare-Metal Servers](https://learn.tradelabsai.com/infrastructure/vps-cloud-and-bare-metal-servers/): Compare VPS, cloud and bare metal servers for running trading bots and systems. Learn costs, latency, reliability, choosing a region and basic server setup.
