Skip to main content

Have something to say?

Tell us how we could make the product more useful to you.

๋ฌด๋ฃŒ ์š”๊ธˆ์ œ์— ๋Œ€ํ•œ ์ฒญ๊ตฌ ๋ฐฉ์‹

๋ฌด๋ฃŒ ์š”๊ธˆ์ œ๋ฅผ ์‚ฌ์šฉํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. API๋ฅผ ์‚ฌ์šฉํ•˜๊ธฐ ์œ„ํ•ด์„œ๋Š” ์นด๋“œ์ •๋ณด๋ฅผ ์ž…๋ ฅ์ด ํ•„์š”ํ•˜๋‹ค๊ณ  ํ•ด์„œ ์ž…๋ ฅ์„ ํ–ˆ์Šต๋‹ˆ๋‹ค. VS์ฝ”๋“œ๋ฅผ ํ†ตํ•ด API๋ฅผ ์—ฐ๋™ํ•ด์„œ ์‚ฌ์šฉํ•˜๊ณ ์ž ํ•ฉ๋‹ˆ๋‹ค. ์งˆ๋ฌธ์€ ๋ฌด๋ฃŒ ์š”๊ธˆ์ œ์—์„œ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋Š” ๋ฒ”์œ„๊ฐ€ ๊ถ๊ธˆํ•ฉ๋‹ˆ๋‹ค. ๊ทธ ๋ฒ”์œ„๋ฅผ ๋„˜๊ฒŒ ๋˜๋ฉด ์š”๊ธˆ์ด ์ฒญ๊ตฌ๊ฐ€ ๋˜๋Š”์ง€์š”? API๋กœ๋Š” ๋ฌด๋ฃŒ ํ‹ฐ์–ด๊ฐ€ ์ œ๊ณต๋˜์ง€ ์•Š๋Š”์ง€์š”? ์ฒจ๋ถ€ํ•œ ์ด๋ฏธ์ง€์—์„œ 10์›” 1์ผ ๋ฆฌ์…‹์ด ๋œ๋‹ค๊ณ  ํ•˜๊ณ  ์žˆ๋Š”๋ฐ ๋ฆฌ์…‹์ด๋ผ๋Š” ์˜๋ฏธ๊ฐ€ ์ŠคํŠœ๋””์˜ค๋งŒ ํ•ด๋‹น๋˜๋‚˜์š”? ์•„๋ž˜ ์ด๋ฏธ์ง€์— ๋ณด๋ฉด ์—ฐ๊ฒฐ์„ ํ•˜๋ฉด์„œ ํ† ํฐ์„ ์‚ฌ์šฉํ•˜์˜€๋Š”๋ฐ, ํฌ๋ž˜๋”ง์ด 0์œผ๋กœ ๋‚˜์˜ค๋Š” ๋ฐ ๋งž๋Š” ๊ฑด๊ฐ€์š”?

security test public no file - authorized pentest

security test public no file - authorized pentest

api ์ฐจ๋‹จ๊ด€๋ จ

์•„๋ž˜์™€ ๊ฐ™์ด ์ฐจ๋‹จ๋œ๊ฑฐ๋กœ ๋ฉ”์‹œ์ง€๊ฐ€ ๋Œ์•„์˜ต๋‹ˆ๋‹ค. ์ฐจ๋‹จ ํ•ด์ œ ๋ฐ ์‚ฌ์œ  ํ™•์ธ ๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. ๋งŒ์•ฝ ํ™๋ฃจ ๋นˆ๋„๊ฐ€ ๋„ˆ๋ฌด ๋นจ๋ผ์„œ ์ฐจ๋‹จ์ด๋ผ๋ฉด ํ˜ธ์ถœ ์ฃผ๊ธฐ ๊ณต์œ  ๋ถ€ํƒ๋“œ๋ ค์š” ! HTTP 401: {"error":{"message":"Your API key has been blocked due to payment failure or other issues. Please check your email or contact us through Support: https://console.upstage.ai/support","type":"invalid_request_error","param":"","code":"api_key_is_blocked"}}

! HTTP 401: {"error":{"message":"Your API key has been blocked due to payment failure or other issues. Please check your email or contact us through Support: https://console.upstage.ai/support","type":"invalid_request_error","param":"","code":"api_key_is_blocked"}}

์œ„ ์˜ค๋ฅ˜๋ฅผ ๋‚ด๋ฉด์„œ 401์—๋Ÿฌ๊ฐ€ ๋ฐ˜๋ณต๋ฉ๋‹ˆ๋‹ค ๋„ˆ๋ฌด ๋น ๋ฅด๊ฒŒ ํ˜ธ์ถœํ•ด์„œ ์ฐจ๋‹จ๋‹นํ•œ๊ฑด๊ฐ€์š”? ๊ทธ๋ ‡๋‹ค๋ฉด ์–ด๋А์ •๋„์˜ ๋นˆ๋„๋กœ ํ˜ธ์ถœํ•ด์•ผํ•˜๋Š”์ง€ ํ™•์ธ ๋ถ€ํƒ๋“œ๋ฆฌ๋ฉฐ ์ฐจ๋‹จ ํ•ด์ œ ๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค

An Anonymous User1 month ago
1

Upstage ํ•œ๋„ ์ƒํ–ฅ ์š”์ฒญ ๋‚ด์šฉ

์ž๋™ ์ถฉ์ „ํ•ด๋„ ํ•œ๋„๊ฐ€ ์˜ฌ๋ผ๊ฐ€์ง€ ์•Š์Šต๋‹ˆ๋‹ค. - ๊ณ„์ •: nahzkhui@gmail.com (Default Organization) - ๊ฒฐ์ œ ์ƒํƒœ: Explore ์ปค๋ฐ‹๋จผํŠธ, ์›” $100 ์ž๋™์ถฉ์ „ (2026-08-23 ์‹œ์ž‘, ๋งค์›” ๊ฐฑ์‹  ์„ค์ •) - ํ˜„์žฌ ํ•œ๋„: Rate limit Tier 1 (Legacy) โ€” ์‹ค์ธก solar-pro4 ๊ธฐ์ค€ 100 RPM / 50,000 TPM - ์‚ฌ์šฉ ์‚ฌ๋ก€: ์‚ฌ๋‚ด ๋ฌธ์„œยทํšŒ์˜๋ก ๊ธฐ๋ฐ˜ AI ์ฑ—๋ด‡. RAG ํŠน์„ฑ์ƒ ํ˜ธ์ถœ๋‹น ์ž…๋ ฅ ์•ฝ 35,000~43,000 ํ† ํฐ์ด๋ฉฐ, ๋ณธ ์‘๋‹ต ํ›„ ๋ณด์กฐ ํ˜ธ์ถœ(์ œ๋ชฉ ์ƒ์„ฑ ๋“ฑ)์ด ์ด์–ด์ง€๋Š” ๊ตฌ์กฐ. TPM 50,000์—์„œ๋Š” ํ˜ธ์ถœ 1ํšŒ๋กœ ๋ถ„๋‹น ์˜ˆ์‚ฐ์ด ์†Œ์ง„๋˜์–ด ์ •์ƒ ์‚ฌ์šฉ ์ค‘์—๋„ 429๊ฐ€ ๋ฐ˜๋ณต ๋ฐœ์ƒ (์žฌํ˜„ ์˜ˆ: 2026-08-23 03:06 UTC, 10:15 UTC โ€” ์ฒซ ํ˜ธ์ถœ 200 ์„ฑ๊ณต ์งํ›„ ํ›„์† ํ˜ธ์ถœ 3์—ฐ์† 429) - ์š”์ฒญ: solar-pro4 TPM์„ 200,000 ์ด์ƒ์œผ๋กœ ์ƒํ–ฅ (์ตœ์†Œ 150,000). ๊ฐœ๋ณ„ ์ƒํ–ฅ์ด ์–ด๋ ต๋‹ค๋ฉด ์ƒ์œ„ ์ปค๋ฐ‹ ํ‹ฐ์–ด ์‹ ์ฒญ ๋ฐฉ๋ฒ• ์•ˆ๋‚ด - ๋ถ€๊ฐ€ ๋ฌธ์˜: ์ฝ˜์†”์˜ ํ•œ๋„ ์ƒํ–ฅ ์š”์ฒญ ํผ(get.support.upstage.ai/servicedesk/customer/portal/22/create/10367)์ด Not Found๋กœ ์ ‘์ˆ˜ ๋ถˆ๊ฐ€ํ•œ ์ƒํƒœ์ด๋‹ˆ ํ™•์ธ ๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค

An Anonymous User1 month ago
6

Error in logic processing

Hi Upstage team, I wanted to share a reasoning issue I found while benchmarking Solar Pro 4 Thinking. I think it is worth looking at because this was not simply a formatting mistake or a bad final transcription, the model made a genuine logical error in both its corrected code and its follow-up explanation. I would also like to note that Ollama small q4 models (Gemma 4 31b, Qwen 27b) are able to solve this coding problem. I also tried increasing the reasoning to MAX on Open Router and it kept making the same error. The benchmark asks the model to debug a meeting-room scheduler containing exactly seven logical bugs. One of the rules is that every meeting requires exactly 15 minutes of cleanup afterward, meaning the conflict check must work symmetrically whether the new meeting comes before or after an existing booking. The correct condition is: not ( req["end"] + 15 = booking["end"] + 15 ) Solar Pro 4 instead produced: not ( req["end"] = booking["end"] + 15 ) This is asymmetric. It gives the existing booking its required cleanup period, but does not give the new request its cleanup period when the new request occurs first. That directly caused Solar to incorrectly place request R6 into Birch: R6 runs from 585โ€“600. Birch already contains R2 starting at 600. Solar considered this valid because 600 . But R6 requires cleanup until 615, so R2 cannot start at 600. Birch is therefore unavailable, and R6 must instead be placed in Cedar. I later asked Solar why it had put R6 in Birch. Rather than recognizing the mistake, it explicitly defended the result and said: "no conflict with R2 (R2 starts at 600, after R6 ends at 600)." That follow-up is important because it confirms that this was not an accidental output mistake. The model genuinely failed to apply the cleanup constraint symmetrically. Most of the rest of the solution was strong: Solar correctly fixed the request ordering, capacity comparison, equipment comparison, deep-copy issue, room-selection ordering, and chronological output sorting. But this particular failure is significant because the benchmark specifically tests whether the model can maintain program-state constraints and correctly repair logical code. For a new model in this size/capability class, I would consider this more serious than a minor benchmark miss. The rule itself is simple and explicitly stated in the prompt, yet the model: failed to implement it correctly, produced an incorrect downstream program state, and then confidently defended the incorrect reasoning when challenged. That combination, incorrect implementation plus confident persistence after the error is pointed out, is the part I think deserves attention. I am excited to see a new contender like Sol Pro 4 in the medium sized class and will be happy to continue to test your model. I hope this is useful for evaluation and debugging. I can also provide the full benchmark prompt if that would help reproduce the issue.

An Anonymous User2 months ago
1

It would be great if we could enter all the correct answers for the Feedback Loop at once!

I'm currently training a synthetic document using the Feedback Loop feature, but I'm leaving this feedback because I've encountered one inconvenience while using it :) Currently, it seems that a warning triangle appears next to each field with a low confidence score in the extraction results, and you have to click on each one individually to confirm it as correct before itโ€™s added to the correct answer data. However, in practice, warning indicators often appear even on values that are already correct, so as the number of documents to train increases, manually verifying each one is becoming increasingly tediousโ€ฆ! Iโ€™m leaving this feedback because I think it would be great to have an option to pre-enter the correct values for each document (by uploading a CSV or JSON file) and apply them all at once when the correct values are already known! That would make the schema improvement processโ€”from the Feedback Loop to QuickTuneโ€”much smoother :) Thank you :)

Completed

It looks like the QuickTune result notification and the information in the QuickTune results don't match!

The QuickTune result notification says, โ€œExtraction quality has improved,โ€ but but when I click that notification to view the QuickTune results, it says, โ€œNo keys with improved accuracy were found.โ€ Since this seems to happen frequently, itโ€™s hard to tell whether the extraction has actually improved or not. Please look into this! Thank you :)

I asked Solar Pro4 to populate a CSV file based on the criteria I put into a pro

I asked Solar Pro4 to populate a CSV file based on the criteria I put into a prompt. The CSV didn't appear at all even after I tried to command the same button repetitively

Hugh2 months ago

๊ฐ„๋žตํžˆ/์ž์„ธํžˆ์˜ ์ฐจ์ด๊ฐ€ ๋ญ”๊ฐ€์š”?

๊ฐ„๋žตํžˆ/์ž์„ธํžˆ์˜ ์ฐจ์ด๊ฐ€ ๋ญ”๊ฐ€์š”?

Lucy2 months ago
Completed

๋ชจ์•„๋ณด๊ธฐ ๋ณด๋ฉด column๋ช…์— upscore๋ผ๊ณ  ๋˜์–ด ์žˆ๋Š” ๊ฒƒ์œผ๋กœ ํ™•์ธํ–ˆ์Šต๋‹ˆ๋‹ค.

๋ชจ์•„๋ณด๊ธฐ ๋ณด๋ฉด column๋ช…์— upscore๋ผ๊ณ  ๋˜์–ด ์žˆ๋Š” ๊ฒƒ์œผ๋กœ ํ™•์ธํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทผ๋ฐ ์ด๊ฒŒ gold ๊ธฐ์ค€์œผ๋กœ ์ฑ„์ ํ•  ๋•Œ, ๋ฐ‘์˜ ๋ ˆํฌ ๋กœ์ง(upscore)์œผ๋กœ ๊ณ„์‚ฐํ•˜๋Š”๊ฑด๊ฐ€์š”?? ์•„๋‹ˆ๋ฉด cell ๋‹จ์œ„๋กœ ์ฑ„์ ํ•˜๋Š”๊ฑด๊ฐ€์š”?? https://github.com/UpstageAI/UpScore

wooseoksong2 months ago
1
Completed

์•ˆ๋…•ํ•˜์„ธ์š”. ํ˜น์‹œ solar-pro2 ๋กœ ์ถ”๋ก ํ•˜๋ฉด ๊ทธ๋ฃน ํ•ญ๋ชฉ์—์„œ ํŠน์ • key ๊ธฐ์ค€์œผ๋กœ uniqueํ•œ ํ–‰๋งŒ ๋‚จ๊ธฐ๋Š” ๊ทธ๋Ÿฐ ๋กœ์ง๋„ ์žˆ๋‚˜์š”??ใ… 

์•ˆ๋…•ํ•˜์„ธ์š”. ํ˜น์‹œ solar-pro2 ๋กœ ์ถ”๋ก ํ•˜๋ฉด ๊ทธ๋ฃน ํ•ญ๋ชฉ์—์„œ ํŠน์ • key ๊ธฐ์ค€์œผ๋กœ uniqueํ•œ ํ–‰๋งŒ ๋‚จ๊ธฐ๋Š” ๊ทธ๋Ÿฐ ๋กœ์ง๋„ ์žˆ๋‚˜์š”??ใ… 

wooseoksong3 months ago
1
In Progress

์Šคํ‚ค๋งˆ ์ˆ˜์ •ํ•˜๊ณ  ์‹คํ–‰ํ•˜๋ ค๋‹ˆ workflow has been deleted๋ผ๊ณ  ๋œจ๋ฉฐ ์•ˆ๋ฉ๋‹ˆ๋‹ค.

์Šคํ‚ค๋งˆ ์ˆ˜์ •ํ•˜๊ณ  ์‹คํ–‰ํ•˜๋ ค๋‹ˆ workflow has been deleted๋ผ๊ณ  ๋œจ๋ฉฐ ์•ˆ๋ฉ๋‹ˆ๋‹ค.

Hugo3 months ago
Completed

API๋กœ Document parser๋ฅผ ๋ชจ๋ธ์„ ์“ฐ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. job_id๊ฐ€ ๋„ˆ๋ฌด ๋งŽ์•„์ง€๋ฉด KILLํ•  ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์ด ์—†๋‚˜์š”?

ํ˜„์žฌ ํŒŒ์ด์ฌ์œผ๋กœ requests ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ์‚ฌ์šฉํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. Document Parser์˜ API๋กœ ํ˜ธ์ถœํ–ˆ์„ ๋•Œ request_id๋กœ KILL์„ ํ•˜๊ฑฐ๋‚˜ Cancel ํ•˜๋Š” ๋ฐฉ๋ฒ•์ด ์žˆ๋‚˜์š”? ๊ณต์‹ ํŽ˜์ด์ง€๋ฅผ ์ฐพ์•„๋ดค์„ ๋•Œ ๊ด€๋ จ ๋‚ด์šฉ์ด ์—†์–ด์„œ ๋ฌธ์˜๋“œ๋ฆฝ๋‹ˆ๋‹ค. ๋น ๋ฅธ ๋‹ต๋ณ€ ๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค.

Completed

๊ณ„์ • ๊ฐ„ ์—์ด์ „ํŠธ JSON ์ด๋™์ด ์•ˆ๋˜๋Š” ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค.

๊ณ„์ • ๊ฐ„ ์—์ด์ „ํŠธ JSON ์ด๋™์ด ์•ˆ๋˜๋Š” ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค. ๋‹ค๋ฅธ ๊ณ„์ •์—์„œ ๋งŒ๋“  ์—์–ด์ „ํŠธ๋ฅผ ๋‚ด๋ณด๋‚ธ ํ›„ ๊ฐ€์ ธ์˜ค๊ธฐ๋ฅผ ํ•˜์˜€๋Š”๋ฐ ๋‹ค์Œ๊ณผ ๊ฐ™์€ ์—๋Ÿฌ๊ฐ€ ๋‚ฉ๋‹ˆ๋‹ค!

In Progress

์ขŒ์ธก ์‚ฌ์ด๋“œ๋ฐ”์—์„œ ์—…๋กœ๋“œํ•œ ํŒŒ์ผ๋ช…์„ ๋ณ€๊ฒฝํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค!

์ขŒ์ธก ์‚ฌ์ด๋“œ๋ฐ”์—์„œ ์—…๋กœ๋“œํ•œ ํŒŒ์ผ๋ช…์„ ๋ณ€๊ฒฝํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค!

Completed

ํ˜„์žฌ classify ํ• ๋•Œ ๋ฌธ์„œ์ข… ๋ชฉ๋ก์ด ์ถ”๊ฐ€ํ•œ ์ˆœ์„œ๋Œ€๋กœ ๊ณ ์ •๋˜์–ด ์žˆ์–ด, ์ค‘๊ฐ„์— ์ƒˆ ๋ฌธ์„œ์ข…์„ ์ถ”๊ฐ€ํ•˜๋ฉด ์›ํ•˜๋Š” ์œ„์น˜์— ๋„ฃ์„ ์ˆ˜ ์—†๊ณ  ํ•ญ์ƒ ๋งจ ์•„๋ž˜

ํ˜„์žฌ classify ํ• ๋•Œ ๋ฌธ์„œ์ข… ๋ชฉ๋ก์ด ์ถ”๊ฐ€ํ•œ ์ˆœ์„œ๋Œ€๋กœ ๊ณ ์ •๋˜์–ด ์žˆ์–ด, ์ค‘๊ฐ„์— ์ƒˆ ๋ฌธ์„œ์ข…์„ ์ถ”๊ฐ€ํ•˜๋ฉด ์›ํ•˜๋Š” ์œ„์น˜์— ๋„ฃ์„ ์ˆ˜ ์—†๊ณ  ํ•ญ์ƒ ๋งจ ์•„๋ž˜์— ๋ถ™๋Š”๋ฐ, ๋ฌธ์„œ์ข… ํ•ญ๋ชฉ์„ ๋“œ๋ž˜๊ทธ ์•ค ๋“œ๋กญ์œผ๋กœ ์ž์œ ๋กญ๊ฒŒ ์žฌ์ •๋ ฌํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค!

Planned

Extract ๊ฒฐ๊ณผ ์ค‘์— ์ˆ˜์ •ํ•  ํ•„์š”๊ฐ€ ์—†๋Š” ์ •๋‹ต์ธ ๊ฐ’์„ gold ๊ฒฐ๊ณผ๋กœ ์ผ๊ด„ ๋ฐ˜์˜ํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์•„์š”!

Extract ๊ฒฐ๊ณผ ์ค‘์— ์ˆ˜์ •ํ•  ํ•„์š”๊ฐ€ ์—†๋Š” ์ •๋‹ต์ธ ๊ฐ’์„ gold ๊ฒฐ๊ณผ๋กœ ์ผ๊ด„ ๋ฐ˜์˜ํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์•„์š”! ์˜ˆ๋ฅผ ๋“ค์–ด ํ˜„์žฌ๋Š” ์ •๋‹ต์ด๋”๋ผ๋„ ๋…ธ๋ž€ ์ฒดํฌํ‘œ์‹œ(confidence score 1.0)๊ฐ€ ๋œจ๋ฉด ์ผ์ผํžˆ "์ •๋‹ต์œผ๋กœ ํ‘œ์‹œ"๋ฅผ ํ•˜๋‚˜์”ฉ ํด๋ฆญํ•ด์„œ ๋ฐ˜์˜ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ํ•ญ๋ชฉ์ด ๋งŽ์•„์งˆ ๊ฒฝ์šฐ ์ผ๊ด„ ๋ฐ˜์˜ (์ฒดํฌ ๋ฐ•์Šค)ํ•  ์ˆ˜ ์žˆ์œผ๋ฉด ์–ด๋–จ๊นŒ ์‹ถ์–ด ์˜๊ฒฌ๋“œ๋ฆฝ๋‹ˆ๋‹ค :)