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
It says Cost$0.25 Input Tokens 54541 Output Tokens 431 Reasoning Tokens — but according to openrouter the cost of z-ai/glm-4.5 is $0.20/M input tokens $0.80/M output tokens, which is much lower. Is this discrepancy due to a bug in opencode?
Where are the 50k+ input tokens coming from for my query and how can I inspect them?
just to provide insight into where the tokens are coming from, looks like vast majority are from the web fetch results, they can be rather expensive depending on website & content
Activity
github-actions commentedon Aug 17, 2025
This issue might be a duplicate of existing issues. Please check:
Feel free to ignore if none of these address your specific case.
rekram1-node commentedon Aug 17, 2025
Looking at openrouter I see:
Input: $0.6/M
Output: $2.20/M
see here
[-]Cost and token usage questions[/-][+]bug: token cost seems inaccurate[/+]nikhilmaddirala commentedon Aug 17, 2025
When I click your link I see the same numbers I cited in my OP.
rekram1-node commentedon Aug 17, 2025
@nikhilmaddirala I was looking at:
But yes you are correct and this appears to be a bug, thank you for reporting
nikhilmaddirala commentedon Aug 17, 2025
spoons-and-mirrors commentedon Aug 19, 2025
somewhat related to #1937 I believe
rekram1-node commentedon Aug 22, 2025
just to provide insight into where the tokens are coming from, looks like vast majority are from the web fetch results, they can be rather expensive depending on website & content
rekram1-node commentedon Dec 28, 2025
[automated] Closing due to 90+ days of inactivity. Feel free to reopen if you still need this!