Claude 3.7 Sonnet [Public Preview]

[matthewisabel]

Claude 3.7 Sonnet is now available in Copilot

See the changelog for Claude 3.7 Sonnet

The new Claude 3.7 Sonnet is now available in Pro, Business, and Enterprise plans across Copilot Chat across Visual Studio Code, Copilot Chat on GitHub.com, and Visual Studio. The model will also be available soon in Jetbrains IDEs.

We'd love to hear your suggestions for improvements and any issues we might see as you start using the new model!

_ 🟢 2025-02-25, 20:45:00 UTC After intermittent instability, we have now rolled out access to all paid Copilot plans._

[hmorneau]

It's out already: https://www.anthropic.com/news/claude-3-7-sonnet

I just tested on Cursor, it's much better.

[matthewisabel]

Cool, hope you'll give it a try on on Copilot as well :)

[hmorneau]

@matthewisabel I just did, and it outperformed Cursor in the first try. Seems like you deployed a good version of it. Thanks!
How can we get rid of the old model like 4o, o1, o3-mini from the list? ;)

[mlesnews]

Using anything but claude-3-7-sonnet thinking feels akin to trying to code with both hands tied behind your back! Please take my money to give more available time without being rate limited. What about the HUUGGE dopamine rush it gives? 🥇

[ghost]

Not everyone has the means to test the models, especially the paid ones. There should be a free version, just like there is for Sonnet 3.5, as I would like to use or test it.

[RebaiFedi]

When will it be available on GitHub Copilot

[spacesnotabs]

Yes, but according to the GitHub Status page, the issue has been resolved, which is why people are still bringing it up.

[ericktreichel]

Yes, but according to the GitHub Status page, the issue has been resolved, which is why people are still bringing it up.

yeah, that "Resolved" status in the status page is very confusing, but people already talked about the meaning of that here 10x as well

[matthewisabel]

Sorry for the confusion today folks, now that we're fully back up with the new model please let us know if you hit any issues.

[sp-aaflalo]

@matthewisabel Are you sure it's fully back up ?
I still don't see it, even when enabled on our organization Copilot Models and Policies. I only see the Claude 3.5 and Gemini 2.0 Flash in any UI, on github or vs code. I only see it in Jetbrains IDE oO

[Ammber666]

Some time ago, my student certification was approved. However, I am unable to use Claude 3.7 and O1.

[tzutoo]

Cursor, Cody, Roo code have announced support for Sonnet 3.7. Windsurf is expected to support it soon. Hope GitHub copilot supports it as well.

[RebaiFedi]

But GitHub Copilot is slow in taking updates..

[hmorneau]

Not today, it's available now! Copilot is really rocking these day. I don't know what happened but they are getting good now.

[lxyesa]

I can now see that the model is available for selection in VSCode, but it is currently not usable and has returned an error: Request Failed: 400 {"error":{"message":"The requested model is not supported.","param":"model","code":"model_not_supported","type":"invalid_request_error"}}

[CRooi]

same here

[kkjdaniel]

Yup model is completely gone for me too.

[razvanphp]

This incident has been resolved.
Posted 2 hours ago. Feb 25, 2025 - 15:45 UTC

Still not shown in my VSCode 🙁

[matthewisabel]

Sorry for the confusion today folks, now that we're fully back up with the new model please let us know if you hit any issues and what you think.

[poetic-design-net]

do you will open it in also for VS Code LM API? @matthewisabel

[muzzlol]

i get the following prompt repeated back to me.

forgive me if im being ignorant, but shouldnt updating the model essentialy be a one liner change? just trying to understand how things work i appreacite everyones effort

[matthewisabel]

Hey are you still seeing this? It is possible this happened during rollout based on timing.

[muzzlol]

Hey are you still seeing this? It is possible this happened during rollout based on timing.

no, everything working perfectly good sir
👍

[hmorneau]

@matthewisabel I was able to output 6000 tokens and it wasn't even the limit. 🥇

Edit: well, that didn't last long, see below.

[hmorneau]

@matthewisabel They nerfed Claude 3.7 thinking already, that was fast. The exact same prompt last night as reported above, I was able to convert that document and get an answer of 6200 tokens.

Now today on a new conversation, same prompt, the same file show that's it's over the context limit (it's in orange).

The answer yesterday was 6000 tokens. The answer today 3500 tokens and it's obviously incomplete.

It didn't last long...

[wuaimtuangnueia]

Does sonnet 3.7 (and think-mode) have the quota of using? Is it the same unlimited as 3.5?

[wuaimtuangnueia]

idk about thhinking, but 3.6 sonnet and 3.7 have same pricing so they probably would'nt rate limit this if it wasn't already

Usage limits are not necessarily set based on price. For example, the o3mini should actually be cheaper than the 4o, but the o3mini is limited to 50 times per 12 hours in copilot.

[matthewisabel]

We have a rate limit for 3.7 that's a bit lower than 3.5 presently as we ensure rollout reaches all users with plans to raise it over the week to 3.5 levels.

[wuaimtuangnueia]

We have a rate limit for 3.7 that's a bit lower than 3.5 presently as we ensure rollout reaches all users with plans to raise it over the week to 3.5 levels.

Will o3mini remove the 50-per-12-hour limit? As mentioned above, o3mini actually costs less than 4o

[pidgeon777]

We have a rate limit for 3.7 that's a bit lower than 3.5 presently as we ensure rollout reaches all users with plans to raise it over the week to 3.5 levels.

Hi @matthewisabel, did you mean over the week(s)? Or the 's' is intentionally missing (I hope so 🙂).

[Yeastiest]

We have a rate limit for 3.7 that's a bit lower than 3.5 presently as we ensure rollout reaches all users with plans to raise it over the week to 3.5 levels.

Please let us know when rates are increased, as many including me have migrated to 3.5 in the meantime, thanks!

[ericc-ch]

Are the thinking/reasoning tokens hidden for the thinking model? I can't seem to find it

[matthewisabel]

We don't show them at the moment but will soon

[ericc-ch]

Thank you for the answer! Nice to hear that, hope it will be shown soon

[devslimbr]

Using Claude Sonnet 3.7, I can barely use it properly. I keep getting rate limited, and now I’m blocked for 2 hours, even on the paid version

[matthewisabel]

We're seeing some error rate elevation with AWS Bedrock and capacity constraints at the moment, we're working actively to resolve

[Aze1337]

We're seeing some error rate elevation with AWS Bedrock and capacity constraints at the moment, we're working actively to resolve

Hello, any eta regarding this? im willing to pay 200$ a month for unlimited or somewhat closer to this for the agentic/edit part with sonnet 3.7! doesnt need extended thinking.

[linacloud-fairy]

When will vision be incorporated into the model?

[matthewisabel]

In the near future we'll add this model into our vision preview

[m4dc4p]

Really want to see this! Then I can upload a screenshot of my web UI and ask for refactors!

[giovannicocco]

Hi! I am getting 500 Internal Server Error and sometimes code 400. I got this issue using Copilot Edits, Cline and Roo Code from VS Code and VS Code Insiders

[LBV2012-26]

Yes, very unstable.

[mmw1984]

[hmorneau]

@mmw1984 and all that yellow on your css and js file mean you are over the context limit.

[mmw1984]

@mmw1984 and all that yellow on your css and js file mean you are over the context limit.

known

[indcoder]

Getting the 500 errors on more than one occassion

[matthewisabel]

This should now be resolved but feel free to reach out if you continue to see issues

[indcoder]

Yes, thank you @matthewisabel for letting me know. For all the 4 prompts I had, I did not encounter any issues.

[ricsi1012]

Is Claude 3.7 Sonnet available in agent mode? I can only see it in 'edit' mode.

[giovannicocco]

I think this morning 4-5am (CT)

[mmw1984]

I think this morning 4-5am (CT)

woww...... thats why I can't find now, No reason why they remove them.

[hmorneau]

I think this morning 4-5am (CT)

woww...... thats why I can't find now, No reason why they remove them.

Still there for me, I guess as long as I don't switch away from it. Just tested and it's working, so much be a UI thing only.

[mmw1984]

working, so much be a UI thing only.

wish its a bug

[matthewisabel]

Sorry for the frustration here with some early instability. You should see 3.7 in Agents/Edits and we're working on enabling the thinking model here as well.

[mmw1984]

Please add Claude 3.7 Sonnet back to Agent mode in VS Code

[owen800q]

Please add Claude 3.7 Sonnet back to Agent mode in VS Code

佢加左，你update下vs code

[mmw1984]

真??! Insider... 再試下update..

Eng Trans: Really??? I am in Insider version, let me try to update again

[mmw1984]

[matthewisabel]

Sorry for the instability today folks, now that we're fully back up with the new model please let us know if you hit any issues and what you think.

[dhe365]

Are there any more infos on the Rate-Limit? I keep getting rate-limited with 3.7 Sonnet and GH Copilot Agent on the Pro Plan.

[mlesnews]

Try to consolidate your requests in one chat, it seems to help, as shorter, rapid requests seem to eat up the rate limit quicker. I change to another llm as well but it’s difficult not using Claude 3.7 Thinking. Like trying to code with your hands tied behind your back. Sincerely, Matthew L. -Sent from Gmail Mobile

…

On Sun, Mar 2, 2025 at 9:43 AM Dennis Hermanns ***@***.***> wrote: Are there any more infos on the Rate-Limit? I keep getting rate-limited with 3.7 Sonnet and GH Copilot Agent on the Pro Plan. — Reply to this email directly, view it on GitHub <#152291 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AATTCBKXISVX64M2FTKGYX32SMKIPAVCNFSM6AAAAABXY2T6ZCVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWGY2DANQ> . You are receiving this because you commented.Message ID: ***@***.***>

[waleed1892]

Still getting rate limits. What's the point of launching model if not allowed to use?

[dooctavian]

It was enabled for a short period, but they then disabled it for models such as Cline / Roo and other agentic coding extensions.

[julien-sarazin]

Hello guys,

I am unable to activate it due to my organization’s policies—it appears to be automatically disabled when I check my settings.
Since I am the owner of the organization, I checked the policies and could not find an entry to change the allowed anthropic model

Could you assist me with this? thank!

[swaroopbutala]

Claude 3.7 Sonnet is now available in Copilot

See the changelog for Claude 3.7 Sonnet

The new Claude 3.7 Sonnet is now available in Pro, Business, and Enterprise plans across Copilot Chat across Visual Studio Code, Copilot Chat on GitHub.com, and Visual Studio. The model will also be available soon in Jetbrains IDEs.

We'd love to hear your suggestions for improvements and any issues we might see as you start using the new model!

_ 🟢 2025-02-25, 20:45:00 UTC After intermittent instability, we have now rolled out access to all paid Copilot plans._

Hello! Any visibility on when it will be generally available (outside Preview)? Enabling preview requires our org to accept the pre release terms which is preventing us from using it. Looking forward to it.

[fishwithfros]

So is Claude 3.7 on Github Pro rate limited to what you'd get if you just used a free account on Claude.ai? Or is it the same limit you'd have with a full account on Claude.ai?

I'm interested, but it would be nice to know what I'm buying. Anthropic doesn't exactly do a great job of positioning the product so you can easily understand what you're buying, and adding Github to the mix only makes it moreso. Anthropic's "5x" sales pitch on their own website is the way you sell detergent, not context windows.

[wuagleugoau]

In my actual tests, the rate limit is only reached when using agents (such as Roo code). When used for chat conversations, the rate limit has not been triggered so far, so it can be considered almost unlimited in terms of chatting.

[fishwithfros]

Does the Github Copilot variant allow you to access the Extended model that's specifically for coding? Or does it only support the mainline 3.5 and 3.7 models?

[wuagleugoau]

Could you please tell me the context length of Sonnet 3.7?

[waleed1892]

I tried copilot sonnet 3.7 on Zed. Context window displayed as 90k. I think it's same in VSC.

[darkensteve]

Sorry, the response hit the length limit. Please rephrase your prompt.

I keep encounter this kind of message even though I always rephrase my prompt, what seems to be the problem here? I'm using the Claude 3.7 Sonnet (Preview) and Claude 3.7 Sonnet Thinking (Preview) btw

[linhisreal]

Has anyone else experienced this issue? After resubscribing to my GitHub Copilot Pro plan, I can hardly use it on the GitHub mobile app, IDEs, or even the CLI. However, I’m unable to access it on the web at all.

[linhisreal]

fixed, sorry i almost forgot this

[schafevormfenster]

We've seen really great code quality in comparison and are able to solve 80-90% of bulk work on several use cases like initial setup, updating the stack, changing modules or parts of the stack and more in mid size code bases.

Bus at the same time we're running into the sonnet usage limits every day after beginning to get into the flow.

Additionally the agent seems slower as it could be. The response times in other environments for the same model (e.g. langdock) are several times faster.

And the context is ignored at least in agent mode. Well configured context files do not have effect. E.g saying to use yarn leads to npm commands. In agent mode this is crucial because it interrupts the round trip and resets the work already done.

We are looking forward for every next update!

[badgermole]

The biggest hurdle to overcome seems to be the inability for a Copilot Pro account user to connect it to their paid/Pro plan for Claude for better capabilities. At least I've not found a way to do that. Enabling that would make it actually useful.

[Wladastic]

You have to install VSCode Insiders to be able to use it.
but it is far from polished.
Rate limit is a problem, not that I complain having it but once it does a huge step and hits the rate limit, you have to let it repeat the whole work to continue, there is not way to just say continue from there.
Copilot will not even remember what it was doing from that point.

[txone]

Edit mode removes all inference models.

[dejvizelo]

@matthewisabel any news on this? I don't seen Claude 3.7 Sonnet Thinking in Edit mode in VS Code 1.99. It was there in VS Code 1.98 in the "Edit" tab of the copilot window.

[debrafeil42]

That's interesting to hear about the advancements with Claude 3.7 Sonnet and its ability to produce excellent content. Speaking of things many people wonder about, especially with dietary restrictions becoming more common, I recently wrote an article on are mms gluten free that delves into which flavors are safe for those avoiding gluten and what to watch out for on the ingredient labels. It's fascinating how even seemingly simple treats can have hidden ingredients. It's great that AI is helping create quality content on a wide range of topics!

[ankiga-MSFT]

I am getting above error when attaching an image. Anyone else facing this issue?