Skip to content

Flint 40B only sent 12 requests to reach free limit #58455

Closed as duplicate
Closed as duplicate

Description

@CNOCTAVE

Description

Have u ever seen a "free model" can only call 12 times in a day? Hilarious. This is a bug.

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot

No response

Operating System

No response

Terminal

No response

Activity

  1. opencode-agent commented on Oct 23, 2026

    @opencode-agent
    Contributor

    Thanks for reporting this. Hitting the free limit on Flint 40B Free after only about 12 requests is frustrating, and I understand why it looks like a bug.

    The daily free allowance for free models is counted and enforced by the OpenCode Console (Zen) service, not by the OpenCode app. The app only shows the limit message the service sends back. That means only the team can check how your usage was counted, and billing and account support isn't handled in GitHub issues. Please email help@anoma.ly with the details: roughly when you hit the limit (with timezone), which model(s) you used, about how many requests you sent, and the exact message you saw. If you've already emailed, the team will get to it, especially now that we've seen it here.

    Please keep email addresses, account details and any payment information out of this public issue and put them in the email instead.

    Related reports, in case they help:

    The bot will close this issue in 1 day.

  2. CNOCTAVE commented on Oct 23, 2026

    @CNOCTAVE
    Author

    OK let's wait for the team. Keep this issue open and remove "pending close" tag.

  3. mslmrezaei commented on Oct 23, 2026

    @mslmrezaei

    Users deserve transparency about the drastic reduction in free model usage

    I have already read the existing issues about free-model rate limiting, including reports from users who are blocked before their first request and users who hit limits after only a few minutes. The responses so far do not adequately address the main concern.

    Free model usage has become so restrictive that it is practically unusable for many users.

    Previously, I could work with free models for extended periods. Now, I can make only a handful of requests before receiving rate-limit errors, sometimes across multiple free models. This is a substantial degradation of the user experience.

    The problem is not simply that rate limits exist. The problem is that users have no clear understanding of what changed, what limits actually apply, or whether the current behavior is intentional.

    We need clear answers from the maintainers

    1. Have free-tier limits changed recently? If so, when did the change take effect, and what were the previous and current limits?
    2. What are the actual limits? Please document the request or token allowances, reset intervals, and any per-model or shared-pool restrictions.
    3. Why are users being rate-limited after only a few requests? Is this expected behavior, a temporary capacity problem, an account-level restriction, or a bug?
    4. Why are multiple free models affected at the same time? If they share a capacity pool, please explain how that pool is managed.
    5. Why do existing reports remain without a clear technical explanation? Users need more than a generic statement that limits are enforced server-side.
    6. Can users expect the previous level of free access to return, or should we assume this is the new permanent policy?

    What I am asking for

    I am not asking for unlimited access to infrastructure that costs money to operate. I am asking for transparency, predictable limits, and an honest explanation of a significant change in functionality.

    If free access has been intentionally reduced, please state that clearly and update the documentation. If this is a bug or capacity issue, please acknowledge it and provide a status update.

    Free models are an important reason people try and continue using OpenCode. When access can disappear after a few minutes without clear limits or useful explanations, users cannot reliably use the product for real development work.

    Please address the specific questions above rather than closing this discussion with a generic rate-limit explanation.

    Environment:

    • OpenCode version: 2.x
    • Operating system: Windows
    • Plan: Free
    • Affected functionality: Multiple free models
  4. CNOCTAVE commented on Oct 23, 2026

    @CNOCTAVE
    Author

    Not only about rate limit, but also about call times limit. 12 times to wait to tomorrow.

    Image
  5. opencode-agent commented on Oct 24, 2026

    @opencode-agent
    Contributor

    Closing this now, @CNOCTAVE. Free-model usage limits are counted on the OpenCode Console (Zen) side, so the team can only look into your account by email. If this is still a problem, please email help@anoma.ly with when it happened, which model you used and the message you saw. Please don't post account or payment details here. Thanks for raising it.

  6. neriousy commented on Nov 4, 2026

    @neriousy
    Member

    Thanks for the report, and sorry for the trouble!

    We're tracking all free-tier quota and limit problems in one place: the pinned issue #59387. Please read it first. Most of these reports are fixed by updating to the latest OpenCode v2 (Desktop v1 users can download it from https://opencode.ai/v2/docs).

    If you're on the latest v2 and still hitting this, please add your details there: OpenCode version, OS, model, and the exact error or reset time shown. Keeping everything in one thread helps us find the cause faster.

    Closing as a duplicate of #59387.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions