I continue to learn how to use my RTK Torch. I am now on Firmware 2.2
There are three choices for the PointPerfect corrections
Menu: PointPerfect Service Selection
Select from the following PointPerfect services compatible with this device:
Disabled
Flex NTRIP/RTCM
Flex MQTT (Deprecated)
x) Exit
I have been using Flex MQTT which I believe to be working fine…. but AI (ChatGPT 5) says to use Flex NTRIP/RTCM
Use: FLEX NTRIP/RTCM
This is the correct and current method for receiving PointPerfect corrections via internet (Wi-Fi) on the SparkFun RTK Torch.
Do NOT Use: FLEX MQTT (Deprecated)
That was an earlier method of receiving corrections from PointPerfect using MQTT over IP.
It’s deprecated and no longer officially supported by u-blox or by SparkFun’s firmware (v2.2 reflects this).
It often does not receive valid corrections due to changes in u-blox’s backend services.
Summary of Options:
Option
Use Case
Status
FLEX NTRIP/RTCM
Best choice for internet delivery over Wi-Fi
Recommended
FLEX MQTT
Old/legacy delivery method
Deprecated
L-Band
If you have an active L-Band antenna and subscription
Alternative, but hardware-dependent
Here’s the key difference:
The RTK Torch has Wi-Fi and Bluetooth but no L-Band antenna.
PointPerfect can be delivered only over IP on the Torch, which means your only working option is the FLEX NTRIP/RTCM method.
MQTT worked on early Torch firmware builds when SparkFun first tested PointPerfect, but u-blox officially deprecated the IP-MQTT delivery mode for PointPerfect in 2024, and the Torch firmware v2.2 reflects that — it will appear as an option, but it won’t reliably receive corrections.
So yes — for the Torch, FLEX NTRIP/RTCM is the correct current setting for PointPerfect corrections over Wi-Fi.
Chris - who is clearly not AI – When I try that setting I get a Point Perfect error that I am not White Listed for that service
And I no longer get RTK FIX, but with FLEX MQTT I do, and I can see the message scroll by I am using PointPerfect for corrections.
From reading PointPerfects Support document, seems like FLEX MQTT is still supported and available. Is FLEX MQTT going away or is ChatGPT having AI Hallucinations?
Your Torch is currently set up with a MQTT (SPARTN) plan. And, yes, MQTT is still supported and available. But if you’d like to move over to the new NTRIP/RTCM service, we can do that.
It’s either-or. Unfortunately you can’t swap service just by changing the Service Selection in the firmware. Sorry if the menu or the docs give you that impression. There’s some work we need to do behind the scenes to move you over to the other plan.
Here’s the quick, practical breakdown for PointPerfect Flex NTRIP/RTCM vs Flex MQTT—with what matters for your RTK Torch in the East TN woods.
What’s the actual difference?
Aspect
Flex NTRIP / RTCM
Flex MQTT (SPARTN over IP)
Protocol & format
TCP NTRIP streams industry-standard RTCM3 corrections direct to the receiver. Works with almost any RTK rover. u-blox
Uses MQTT to deliver compact SPARTN SSR messages; a client/library on the device turns SPARTN into RTCM for receivers like ZED-F9P. developer.thingstream.io
Time-to-fix & stability
Generally faster and more stable on SparkFun gear because it’s native RTCM end-to-end. Users report better, more consistent fixes vs SPARTN→RTCM path. docs.sparkfun.com
Extra decode/convert step can add ~60 s and introduce variability; “OK accuracy (not as good as RTCM service)” per SparkFun docs. docs.sparkfun.com
Bandwidth
A bit heavier; still small (kB/min), but continuous TCP session. trac.gateworks.com
Most bandwidth-efficient (SPARTN is compact) and resilient to brief drops thanks to message design. Still needs IP data. developer.thingstream.io
Device fit (RTK Torch)
Recommended / supported now on newer SparkFun firmware (Torch, EVK, etc.). docs.sparkfun.com
Historically available, but SparkFun guidance and user reports favor NTRIP/RTCM on current firmware due to reliability. docs.sparkfun.comSparkFun Community
Coverage when cell dies
Dies with cell data.
Also dies with cell data. (SPARTN over L-band satellite is the way to ride through cell gaps—but Torch lacks L-band hardware/antenna, so that’s not an option on the Torch.) developer.thingstream.io
Accuracy (service)
Flex is PPP-RTK: ~3–6 cm with seconds-level convergence in supported regions. (Same core service.) u-blox
Same core service & accuracy target; delivery path is the difference. support.thingstream.io
Cost differences
For PointPerfect Flex the pricing is by connected-hours, independent of whether you pull via NTRIP/RTCM or MQTT over IP. Public references show entry plans around $5.90/month for 100 hours, with higher tiers lowering the per-hour rate. (Exact numbers can change, but protocol choice does not change the price.) portal.thingstream.iou-bloxArduSimple+1
What I’d use on your RTK Torch (Sweetwater, TN forests)
Use Flex NTRIP/RTCM as your PointPerfect delivery on the Torch. It’s the path SparkFun currently documents as the better performer on their firmware, with fewer “gotchas.” docs.sparkfun.com+1
MQTT/SPARTN over IP brings no cost advantage on Flex for the Torch and tends to be less consistent on that device family. docs.sparkfun.com
I have not seen a specific End of Life statement for the service from U-blox (not sure if they do those), but IMO, based on how they have revised their service offerings, I doubt they keep it long term.
As far as ChatGPT, it seems to find a fact or statement and then make assumptions. I have had it sometimes give me good info, but then I have had it straight out lie to me. When using it instead of search for a quick find on library method/function calls (or for WordPress hooks)e, it has many times seemingly “made up the answer.” I confront it, ask it why it lied, and it just tells me “Good catch Doug, you’re right on. Here’s the way …” and then it continues to lie again. When it comes to code, I write my own and search the docs. It can’t be trusted. For general topics? Caveat emptor. P.S. - Claude AI does seem to be a bit more honest and say when it doesn’t know an answer.
@ChrisO - $5.90 is for MQTT based service which we have been told is EOL’d. New accounts will be maintained but future customers will not be given access. Also, we’ve found the MQTT based corrections to be not nearly as good as the RTCM/NTRIP corrections. RTCM/NTRIP is my recommendation.
We have baked our ZTP profile into the RTK Firmware so that users give us their device ID, we whitelist that ID and charge the user $15/month, then when a user provisions, our system handles all the NTRIP credentials, prepopulating so folks don’t have to mess about. We tried to make the user experience as simple as possible, but yes, SparkFun is reselling PointPerfect’s service. If you want to go direct to PointPerfect and get the RTCM/NTRIP service for cheaper, you can. You’ll have to copy/paste NTRIP credentials (a bit of hassle), and you may or may not be given access. Historically PointPerfect was a bit cagey about wanting to only deal with companies, not individual users, but I think they started opening up that requirement a bit. YMMV.
WRT chatgpt, I’ve been lied to many times (frustrating). I also want to point out that now that we’ve listed the chatbot response “What’s the actual difference?” on our forum, the next round of training of chatbots will scrap our forum for training material, then use that post as a point of fact, and base future responses on it. When in reality, who knows if the chatbot was ever really correct. A death spiral of self fulfilling incorrect prophecies. Oh dear.
OK, I pay $8 to SparkFun for the MQTT for now, so I guess I will stay with MQTT until I am “terminated” [More AI Robot references] My neighbor is a retired Electrical Engineer and I will try to convince him to setup an NTRIP Server listed with RTK2go.com Once I get my key markers set on the property E6 level accuracy will be fine. I’m going to post some accuracy information from some tests today as a separate thread. I think I am about ready to tackle the farm projects once the leaves fall down. Thanks for all your help.
Use: FLEX NTRIP/RTCM
Do NOT Use: FLEX MQTT (Deprecated)
Summary of Options: