잠재력은 뛰어나지만, 너무 쓰질 못합니다.
저는 Upstage의 뛰어난 잠재력을 최대로 발휘하길 바랍니다. Solar Pro 4 는 Gemini의 3.5 Flash-Light보다 뛰어난 성능을 가지고 있습니다. 하지만 api 중심인 게 너무 수익에 안 좋은 영향을 미치는 듯 합니다. Mistral보다 더 뛰어난 서비스를 만들어놓고 커넥터 기능도 만들어놓고 일반 사용자들에게 왜 공개하지 않습니까? 유료 요금을 만들고 상용 서비스와 앱을 구축하고 퍼줄 컴퓨팅 자원 줄이고 유료요금제 홍보하면 Mistral을 뛰어넘는 LLM 서비스가 될 수 있을 것입니다. 응원합니다.
무료 요금제에 대한 청구 방식
무료 요금제를 사용하고 있습니다. API를 사용하기 위해서는 카드정보를 입력이 필요하다고 해서 입력을 했습니다. VS코드를 통해 API를 연동해서 사용하고자 합니다. 질문은 무료 요금제에서 사용할 수 있는 범위가 궁금합니다. 그 범위를 넘게 되면 요금이 청구가 되는지요? API로는 무료 티어가 제공되지 않는지요? 첨부한 이미지에서 10월 1일 리셋이 된다고 하고 있는데 리셋이라는 의미가 스튜디오만 해당되나요? 아래 이미지에 보면 연결을 하면서 토큰을 사용하였는데, 크래딧이 0으로 나오는 데 맞는 건가요?
Pi Agent와 연동하여 사용시 Rate Limit에 걸리는 문제
안녕하세요! Pi Agent에 Solar Pro 4를 연동하여 사용을 하고 있습니다. 행사때 받은 $10의 크레딧이 있지만, Tier 0 이어서 그런지 기존 문서를 분석하고 새로운 word 문서를 작성하는 task 명령 하나만 내려도 바로 Rate Limit 에러가 발생해버려서, 사실상 Pi Agent에서는 사용하기 힘든 상황입니다. 혹시나 Credit Card를 걸어놓으면 나아질까 하여 Credit Card를 등록을 하였습니다만, Tier 0 상태인건 여전하고, Pi Agent를 통해서 task를 하나 실행하기도 힘든건 여전한 상황입니다. 개인이 사용하는거라 큰 금액을 미리 결제하기엔 부담스럽고, 한 달에 $10 이내로 사용을 희망하고 있고, 그래도 한도 내에서는 Pi Agent 로 사용시 에러없이 사용하고 싶습니다. 현재 구조적으로 이러한 Rate 의 조정이 힘든걸까요? 아무래도 금액이 작다보니 안될것 같기도 하고… 궁금하여 문의 드립니다! 감사합니다.
국산 ai라길래 한번 사용해볼려고하는데,
국산 ai라길래 한번 사용해볼려고하는데, 뭐 이렇게 접근성이 안좋나요? gpt,클로드,제미나이 등과 비교했을때 일반 사용자가 접근하기 너무 안좋아요. 아직 ai 성능이 부족해서 일부러 접근성을 개선을 안하는건가 싶기도 하지만... 그래도 일반 사용자가 많이 사용해야 성능 개선에 도움이 되지 않나요? 아쉬움에 글 남깁니다.
api 차단관련
아래와 같이 차단된거로 메시지가 돌아옵니다. 차단 해제 및 사유 확인 부탁드립니다. 만약 홏루 빈도가 너무 빨라서 차단이라면 호출 주기 공유 부탁드려요 ! 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"}}
위 오류를 내면서 401에러가 반복됩니다 너무 빠르게 호출해서 차단당한건가요? 그렇다면 어느정도의 빈도로 호출해야하는지 확인 부탁드리며 차단 해제 부탁드립니다
Upstage 한도 상향 요청 내용
자동 충전해도 한도가 올라가지 않습니다. - 계정: nahzkhui@gmail.com (Default Organization) - 결제 상태: Explore 커밋먼트, 월 $100 자동충전 (2026-08-23 시작, 매월 갱신 설정) - 현재 한도: Rate limit Tier 1 (Legacy) — 실측 solar-pro4 기준 100 RPM / 50,000 TPM - 사용 사례: 사내 문서·회의록 기반 AI 챗봇. RAG 특성상 호출당 입력 약 35,000~43,000 토큰이며, 본 응답 후 보조 호출(제목 생성 등)이 이어지는 구조. TPM 50,000에서는 호출 1회로 분당 예산이 소진되어 정상 사용 중에도 429가 반복 발생 (재현 예: 2026-08-23 03:06 UTC, 10:15 UTC — 첫 호출 200 성공 직후 후속 호출 3연속 429) - 요청: solar-pro4 TPM을 200,000 이상으로 상향 (최소 150,000). 개별 상향이 어렵다면 상위 커밋 티어 신청 방법 안내 - 부가 문의: 콘솔의 한도 상향 요청 폼(get.support.upstage.ai/servicedesk/customer/portal/22/create/10367)이 Not Found로 접수 불가한 상태이니 확인 부탁드립니다
The API service is still in beta testing.
I'm using the Chat Completion API to request structured output, but the response is often truncated without any warning ("finish_reason":"stop"). JSON escaping often fails. Also, whether it’s because I just created the API key or because I’ve hit the rate limit, requests that initially returned a response within 10 seconds now often take over 100 or 200 seconds under the same conditions. I’ve also registered a payment method, but it doesn’t seem to make a difference. I gave up while running benchmarks to debug the "structured output" error. The model’s performance doesn’t seem bad, but the service quality makes it difficult to put it to immediate use. For reference, all service statuses are showing green. I started with `gemini-2.5-flash` to try out a Korean model or one served domestically, but switched to `solar-pro4`—it’s been quite a struggle. The sorrow of a citizen of a developing country ㅠ
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 585–600. 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.
I’d like to share my experience working with the Solar API.
Hello I was wondering if I could use Solar to improve my Korean writing skills, I’m sharing the results of my personal experiment. I hope you find this helpful.
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 it’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 tedious…! I’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 process—from the Feedback Loop to QuickTune—much smoother :) Thank you :)
It looks like the QuickTune result notification and the information in the QuickTune results don't match!
The QuickTune result notification says, “Extraction quality has improved,” but but when I click that notification to view the QuickTune results, it says, “No keys with improved accuracy were found.” Since this seems to happen frequently, it’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
Is there a way to obtain a Solar Open 2 API key?
Like everyone else, I’ve been using DS V4 for a while now, and I use a variety of models—including Kimi, MIMO, OpenCode, GLM, and more—through my annual subscription. At first, just looking at the benchmark results, I thought, “Does this even mean anything to me?” But then I ran two problems through Kimi K2.6, DS V4 Flash, Solar Open2, and GPT5.6 Sol—and Solar Open2 and GPT5.6 Sol got them exactly right. This made me wonder if their actual performance in coding might be even better than what the benchmark results suggest. I’m also active in the community of a U.S.-based startup that provides OpenWeight APIs, and while discussing this, https://open2-beta.upstage.ai/ , but while some people got a 403 error, others were able to access it. I wonder if there are countries where the page doesn’t load. While international service seems unlikely due to language support issues, I thought we might be able to try it out in Korea and English-speaking regions if the performance is decent. If anyone has a trial OpenAI-compatible SolOpen2 API and key, or knows a way to top up and use it, I’d appreciate it if you could let me know.
모아보기 보면 column명에 upscore라고 되어 있는 것으로 확인했습니다.
모아보기 보면 column명에 upscore라고 되어 있는 것으로 확인했습니다. 근데 이게 gold 기준으로 채점할 때, 밑의 레포 로직(upscore)으로 계산하는건가요?? 아니면 cell 단위로 채점하는건가요?? https://github.com/UpstageAI/UpScore
클로드 코드X업스테이지
https://console.upstage.ai/ko/docs/integrations/claude-code 모델을 바꿔도 같은 에러 메시지나 나오네요 현재 지원을 안하는 걸까요??
안녕하세요. 혹시 solar-pro2 로 추론하면 그룹 항목에서 특정 key 기준으로 unique한 행만 남기는 그런 로직도 있나요??ㅠ
안녕하세요. 혹시 solar-pro2 로 추론하면 그룹 항목에서 특정 key 기준으로 unique한 행만 남기는 그런 로직도 있나요??ㅠ