You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When using Github copilot models, the cost tracker is irrelevant as it always stays at $0.00. Instead, is it possible to display the premium requests quota? See below image as an example from VS code copilot extension.
As a github copilot user, I think this would be a great addition to the software. Not having to open up the browser to look at remaining premium requests would be such a good quality-of-life improvement.
Sorry for delay @berenar I think we should wait for opentui to be wrapped up before a PR is attempted here. Another thing we need to surface that currently isn't being surfaced is retries.
I recently added some logic that will allow us to display the # of retries, if it is retrying, etc.
And that would also tie into this because some plan quotas are rate limited and we do exponential backoffs with awareness of the rate limit headers so there are a few moving pieces here.
That said I do like your proposal I just thing it will be best to revisit in a week once opentui has a little less stuff in motion
This same issue applies to z.ai Coding Plans. Cost tracking shows $0.00, but users have no visibility into their prompt quota. Even worse, z.ai does not even have an api call to track this.
Not ideal however a possible approach:
Optional quotas config per provider, make it configurable per model: for example glm4.6: Lite: 120 prompts/5h , Pro: 600 prompts/5h, Max: 2400 prompts/5h
Track rolling window prompt count per configurable time window.
Display alongside cost/even hide cost for flat fee plan: "Cost: $0.00 | Usage: 87%" example based upon 104 requests of 120 limit)
Reacted by Jakub Szczepaniak and Chris Schindlbeck
I have seen Claude Opus 4.5 (preview) gone from 1x to 3x when "preview" title was removed, and it made me cry when I found out I was not hallucinating in VS Code,
Theses changes can be devastating to the premium requests count (been here), I would be nice if it does not rely on manual update of hardcoded constants
Reacted by Benoit de Chezelles, Myōboku and Gethin Davies
There should also be a way to show the model multiplier in the models selection UI & in the upcoming usage UI / sidebar
I dug into the multiplier adding to opencode, and it’s not straightforward. The Copilot /models API only returns billing.multiplier if you call it like an IDE (Editor-Version, Editor-Plugin-Version, Copilot-Integration-Id, VScode-SessionId/MachineId, plus a Copilot token). With the normal GitHub OAuth token opencode uses, the endpoint 404s or says “token not authorized,” so there’s no clean/official way to fetch multipliers with the current implementation.
What I ended up doing is a bit hacky: I reuse a local VS Code Copilot app token to mint a Copilot token, send the IDE headers, and then read billing.multiplier from /models. See: Joost1982@4c2cf2a
It works on my machine (Debian), but it’s no real solution.
What about just hardcoding the multipliers? They rarely change
they often change, sometimes they even get more expensive under high load/demand, and show stuff like this:
they often change, sometimes they even get more expensive under high load/demand, and show stuff like this
How often? I did see just one change in 6 months - promotional 1x for Opus 4.5 for (1 or 2 weeks) and it was advertised that it will change. And similar for Grok Code, but somehow I still have it at 0x, while on copilot page it is listed as 0.25x.
I have not seen changes to multiplier based on load, your screenshot also doesn't show that. Models might be slow to respond, or not respond at all, but this is not change of multipliers.
they often change, sometimes they even get more expensive under high load/demand, and show stuff like this
How often? I did see just one change in 6 months - promotional 1x for Opus 4.5 for (1 or 2 weeks) and it was advertised that it will change. And similar for Grok Code, but somehow I still have it at 0x, while on copilot page it is listed as 0.25x.
I have not seen changes to multiplier based on load, your screenshot also doesn't show that. Models might be slow to respond, or not respond at all, but this is not change of multipliers.
Well, just as example, not much time passed and we see this as of now:
But yes, i did see multiplier based on load once or twice in the entire time, so it does happen but is rare
This is a scandal! They're making the models significantly more expensive! That's not a 10% increase, not 50%, not even 100%. They're making all models 6 to 9 times more expensive!That's a 600% to 900% increase! And at the same time, they're cutting the quota of pro accounts in half! That's another 100% nasty and hidden cost increase! So in total, they're increasing the cost 10 fold, that's a whopping 1000% price hike!
1 AI credits = $0.01 USD, so a $10 budget covers 1,000 AI credits.
The pro plans cost 20$, but now they contain $10 worth of "AI credits"! This is a scam! And GitHub should be sued with a class lawsuit!
Looks like they're reserving their resources for other purposes (e.g., the illegal aggression and attack against Iran) and sacrificing all paying customers, even outside the US, for that.
Activity
martinhpedersen commentedon Jul 8, 2025
FYI - Don't recall where I found it, but the data is available through this endpoint:
curl https://api.github.com/copilot_internal/user -H "Authorization: Bearer $COPILOT_API_KEY" -H "Content-Type: application/json"If anyone is interested in a quick alias to get the current quota/usage:
FareedFarag commentedon Jul 10, 2025
How do you get
COPILOT_API_KEY? Copilot doesn't issue API keys as far as I know.asadmoosvi commentedon Jul 26, 2025
As a github copilot user, I think this would be a great addition to the software. Not having to open up the browser to look at remaining premium requests would be such a good quality-of-life improvement.
berenar commentedon Oct 27, 2025
Here's a curl that uses your GitHub Copilot Oauth token instead:
As a user of Copilot, having this info in the UI would be very useful. I'm happy to implement this if the authors also see its value.
cc @thdxr
rekram1-node commentedon Oct 27, 2025
@berenar how would you go about implementing it? There will probably be other providers that have special billing things like copilot too
This would be welcome but we would probably need to discuss how it would be shown in the ui
berenar commentedon Oct 28, 2025
Providers support
Well, so far I've only used Claude (subscription based), GitHub Copilot and Zen.
I think the rest of supported providers are not subscription based (yet...), therefore they would not need this feature
UI
On how to show it in the UI, that's yours to decide :)
I would leave the top right corner for info related to the current session
And instead use the bottom right corner to show the provider limits

The info to display would change based on the provider being used
Claude
Copilot
wdyt @rekram1-node ?
rekram1-node commentedon Oct 29, 2025
Sorry for delay @berenar I think we should wait for opentui to be wrapped up before a PR is attempted here. Another thing we need to surface that currently isn't being surfaced is retries.
I recently added some logic that will allow us to display the # of retries, if it is retrying, etc.
And that would also tie into this because some plan quotas are rate limited and we do exponential backoffs with awareness of the rate limit headers so there are a few moving pieces here.
That said I do like your proposal I just thing it will be best to revisit in a week once opentui has a little less stuff in motion
itse4elhaam commentedon Nov 25, 2025
Hey, would love this!!!
Any plans on this?
rekram1-node commentedon Nov 26, 2025
No immediate plans but we should think about how we wanna show it
flupkede commentedon Dec 4, 2025
This same issue applies to z.ai Coding Plans. Cost tracking shows $0.00, but users have no visibility into their prompt quota. Even worse, z.ai does not even have an api call to track this.
Not ideal however a possible approach:
quotasconfig per provider, make it configurable per model: for example glm4.6: Lite: 120 prompts/5h , Pro: 600 prompts/5h, Max: 2400 prompts/5hojsef39 commentedon Dec 11, 2025
Would love to see this for Github and Anthropic, i use both and id love to see how much time i have left before i have to think for myself again :D
rosematcha commentedon Dec 17, 2025
Agreed, would love to see this implemented for Copilot, Anthropic, and Codex subscription plans!
peixotorms commentedon Dec 30, 2025
Copilot seems straightforward with just an api call, please add it to opencode.
amaduswaray commentedon Jan 7, 2026
We just started using OpenCode at work, and this would be useful! Are there any requirements beyond the contribution guide to submit a PR on this?
8 remaining items
slhad commentedon Feb 6, 2026
I have seen Claude Opus 4.5 (preview) gone from 1x to 3x when "preview" title was removed, and it made me cry when I found out I was not hallucinating in VS Code,
Theses changes can be devastating to the premium requests count (been here), I would be nice if it does not rely on manual update of hardcoded constants
sTiKyt commentedon Feb 11, 2026
but would be nice to see numeric values, not percentages imo
sTiKyt commentedon Feb 11, 2026
they often change, sometimes they even get more expensive under high load/demand, and show stuff like this:
krzyk commentedon Feb 11, 2026
How often? I did see just one change in 6 months - promotional 1x for Opus 4.5 for (1 or 2 weeks) and it was advertised that it will change. And similar for Grok Code, but somehow I still have it at 0x, while on copilot page it is listed as 0.25x.
I have not seen changes to multiplier based on load, your screenshot also doesn't show that. Models might be slow to respond, or not respond at all, but this is not change of multipliers.
garthendrich commentedon Feb 28, 2026
any updates?
tapajos commentedon Mar 20, 2026
Any plan to add it?
sTiKyt commentedon Mar 21, 2026
Well, just as example, not much time passed and we see this as of now:
But yes, i did see multiplier based on load once or twice in the entire time, so it does happen but is rare
lukasbash commentedon Mar 28, 2026
Any update? Especially just polishing #768 (comment) would bring so much benefit for a fair effort for the community!
csj0oe commentedon Apr 28, 2026
Copilot will soon (June 1, 2026) switch to usage-based billing, see:
https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals
llucax commentedon Apr 29, 2026
I discovered this amazing plugin: https://github.com/slkiser/opencode-quota.
javad-ent commentedon May 11, 2026
This is a scandal! They're making the models significantly more expensive! That's not a 10% increase, not 50%, not even 100%. They're making all models 6 to 9 times more expensive! That's a 600% to 900% increase! And at the same time, they're cutting the quota of pro accounts in half! That's another 100% nasty and hidden cost increase! So in total, they're increasing the cost 10 fold, that's a whopping 1000% price hike!
Check it for yourself:
https://docs.github.com/en/copilot/reference/copilot-billing/model-multipliers-for-annual-plans
https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals
The pro plans cost 20$, but now they contain $10 worth of "AI credits"! This is a scam! And GitHub should be sued with a class lawsuit!
Looks like they're reserving their resources for other purposes (e.g., the illegal aggression and attack against Iran) and sacrificing all paying customers, even outside the US, for that.
FareedFarag commentedon May 14, 2026
Given GitHub's recent switch from premium requests to AI credits as their billing unit, this makes the scope of this issue irrelevant. Closing.
javad-ent commentedon May 17, 2026
Are you planning to show the credit usage then?
FareedFarag commentedon May 18, 2026
I'm not a maintainer for OpenCode. I don't get to decide.