我用了一会儿 GPT-6.1-Terra 模型。这可能是第一个跨越门槛、让我觉得用起来完全不排斥的非前沿模型。感觉就像是稍微简化版的 6.…

@DraftLogic_ 回复 ♥ 0

@petergostev Would you recommend it even for coding on a 20$ plus plan over Sol?

原文

@reddygtvs 回复 ♥ 4

@petergostev Is it any faster tok/s wise? Thinking of getting back to a plus plan to try it out

原文

@ThisisChrisjin 回复 ♥ 2

@petergostev Thoughts about it as a daily driver for openclaw agents, unless its coding work etc??

原文

@eapyk 回复 ♥ 0

@petergostev gpt 6.1 sol very good for 20$ budget and also good usage tbh

原文

@arb5z 回复 ♥ 0

@petergostev felt like a simpler sol after a bit. what did it get wrong?

原文

@darrensy_s 回复 ♥ 0

@petergostev And it is really fast as well, just tried with video editing

原文

@ceasarxuu 回复 ♥ 0

@petergostev 我只是不希望它像 sol 那样慢，太慢了太慢了，做不了任何工作

原文

@YuchaoShang 回复 ♥ 0

@petergostev “non-frontier model that crosses the threshold” seems very interesting, I think there will have lots of open source models with exact descriptions coming out and competing on cost efficiency.

原文

@BlackthorneAI 回复 ♥ 0

@petergostev The best model isn't always the smartest one, it's the one you can afford to keep working. Terra sounds like a strong default for everyday tasks, while Sol still earns its place when the extra reasoning matters. This comment was written with Terra 6.1, using @CryptoReplyGuy1.

原文

@jozefizso 回复 ♥ 0

@petergostev Computer use? What for though?

原文

@nixus404 回复 ♥ 1

@petergostev Aún estoy apenas empezando a probar 6.1 Terra y por ahora en 2 pruebas que hice contra 6.1 Sol ha sido de media 6 veces más rápido Terra!!!!! Que locura de rapidez⚡️

原文

@Moblacksoil 回复 ♥ 0

@petergostev Curious what you'd still hand to Sol instead

原文

@GrimbergYuval 回复 ♥ 0

@petergostev So basically tell 6.1 sol to plan and verify 6.1 terra as his worker?

原文

@Ooommm59You 回复 ♥ 0

@petergostev For 20$ is it going to replace Deepseek-v4.1-flash for me? better quality?

原文

@PHATPHAT7 回复 ♥ 0

@petergostev That’s a meaningful shift if it feels good enough for everyday use without constantly needing the frontier model oneself

原文

@victoria_neiman 回复 ♥ 0

@petergostev agreed on the sol vs terra take. in our code gen test terra built the whole scene for $0.95 in 31 minutes. opus was prettier light but 5x the cost. for most workloads sol is overkill now https://x.com/thehypedotnews/status/2114799954619490582?s=20

原文

@jonnyboy 回复 ♥ 3

@petergostev 6.1 terra feels like it was optimized to run dots for $20 / month users

原文

@YourAKShaw 回复 ♥ 0

This might be Terra's biggest win: becoming the default workhorse rather than another benchmark champion. For long-running agents, stretching usage limits matters enormously. Have you noticed any difference in how Terra handles blockers, retries, or context-heavy tasks compared to Sol?

原文

@jjmilano 回复 ♥ 0

@petergostev I've been using GPT-6.1-Terra for a bit, it did a lot of work but the 5hours limit drained fast as usual. but in the other hand it accomplished a lot of what i asked for or partially smh

原文

@shaunralston 回复 ♥ 0

@petergostev Agreed Peter . . . Funny how parts of X judge a model by how well it plays Minecraft, while dismissing what matters to businesses: reliability, cost, and getting real work done. If you care about applied AI, Terra is a big deal. Not every breakthrough needs to win a video game.

原文

@QuantizedDen 回复 ♥ 1

@petergostev it's promising in terms of pricing, but it's very lazy https://x.com/atomic_chat_hq/status/2114811032816476638?s=20

原文

@samongaro_ 回复 ♥ 0

@petergostev Solid workhorse

原文

@THEJATMN 回复 ♥ 2

@petergostev Im having a hell of a time trying to use terra 6.1 it just keeps giving up on its own tasks and refusing to complete them.

原文

@LogosInstHQ 回复 ♥ 0

@petergostev Opus 5.5

原文

@mktpavlenko 回复 ♥ 1

@petergostev "Don't mind using" is an underrated bar. Most people don't need the best model, they need one that doesn't make them check every answer twice.

原文

@OhChadol 回复 ♥ 1

@petergostev 속도가 빠르고+작은단위로 시킨것만 잘 한다면 최고의 모델 아닐까요

原文

@whb0821 回复 ♥ 2

@petergostev 模型选择越来越务实了。日常任务用便宜、稳定的模型，难题再交给最强的模型，长期算下来可能更划算。以后拼的不是谁只用一个顶级模型，而是谁更会分配任务。

原文

@retropragma 回复 ♥ 0

@petergostev Doesn't seem like you're qualified to give that advice tbh. Did you not see the terminal bench graph?

原文

임베드 보드

评论 28