Free model lineup has moved - #73
Open
github-actions[bot] wants to merge 1 commit into
Open
Conversation
github-actions
Bot
force-pushed
the
lineup/auto
branch
4 times, most recently
from
September 1, 2026 15:04
a9f3641 to
8794183
Compare
Opened by .github/workflows/lineup.yml. Additions go at the end of
the list and nothing is reordered, because the first entry is what a
fresh session starts on and what an automatic failover lands on, and
that is a judgement this workflow does not make. Removals are models
the provider has not served for seven days or more; an absence
shorter than that is reported and left alone, because hy3-free came
back after two. The report below says which is which.
No key in `OPENCODE_API_KEY`, so the probes below carried no `Authorization` header. The free lineup answers without one; a paid model replies `Missing API key`, which is what prices it.
### opencode
64 models served, 8 of them free by the profile's rule, 9 named in the profile.
**Changed:**
- the profile's list does not name `ling-3.0-flash-fin-free`
- `laguna-s-2.1-free` stopped answering
- `ling-3.0-flash-fin-free` answers again
- `nemotron-3-ultra-free` stopped answering
- `laguna-s-2.1-free` is served but stopped answering
- `nemotron-3-ultra-free` is served but stopped answering
- `ling-3.0-flash-fin-free` is answering again
**Free and served, not named in the profile**
- `ling-3.0-flash-fin-free` — 1.08s, 0 chars, 7 tool calls
**Named in the profile, not served**
- `hy3-free` — missing since 2026-08-30 (3 days)
- `x-preview-f-free` — missing since 2026-08-27 (6 days)
**Served, and could not answer** — in the catalogue, in the picker, and failing every probe
- `deepseek-v4-flash-free` — failing since 2026-08-25 (8 days) — HTTP 400: {"error":{"type":"server_error","message":"Error from provider (Console): Upstream request failed: Model is unavailable.
- `laguna-s-2.1-free` — failing since 2026-09-02 — HTTP 503: {"error":{"type":"server_error","message":"Error from provider (Console): Upstream request failed: Endpoint is unavailab
- `muse-spark-1.2-contributor-free` — failing since 2026-08-25 (8 days) — HTTP 500: {"type":"error","error":{"type":"error","message":"Internal server error"}}
- `nemotron-3-ultra-free` — failing since 2026-09-02 — 200 and an empty completion in 67.97s
24 unclassified name(s) went unprobed against the budget; they will be picked up on the next run.
Appended to `profiles/rcc.toml`: `ling-3.0-flash-fin-free`
Put back in the picker, answering again: `nemotron-3.5-lightning-free`
github-actions
Bot
force-pushed
the
lineup/auto
branch
from
September 2, 2026 14:45
8794183 to
bc36efc
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No key in
OPENCODE_API_KEY, so the probes below carried noAuthorizationheader. The free lineup answers without one; a paid model repliesMissing API key, which is what prices it.opencode
64 models served, 8 of them free by the profile's rule, 9 named in the profile.
Changed:
ling-3.0-flash-fin-freelaguna-s-2.1-freestopped answeringling-3.0-flash-fin-freeanswers againnemotron-3-ultra-freestopped answeringlaguna-s-2.1-freeis served but stopped answeringnemotron-3-ultra-freeis served but stopped answeringling-3.0-flash-fin-freeis answering againFree and served, not named in the profile
ling-3.0-flash-fin-free— 1.08s, 0 chars, 7 tool callsNamed in the profile, not served
hy3-free— missing since 2026-08-30 (3 days)x-preview-f-free— missing since 2026-08-27 (6 days)Served, and could not answer — in the catalogue, in the picker, and failing every probe
deepseek-v4-flash-free— failing since 2026-08-25 (8 days) — HTTP 400: {"error":{"type":"server_error","message":"Error from provider (Console): Upstream request failed: Model is unavailable.laguna-s-2.1-free— failing since 2026-09-02 — HTTP 503: {"error":{"type":"server_error","message":"Error from provider (Console): Upstream request failed: Endpoint is unavailabmuse-spark-1.2-contributor-free— failing since 2026-08-25 (8 days) — HTTP 500: {"type":"error","error":{"type":"error","message":"Internal server error"}}nemotron-3-ultra-free— failing since 2026-09-02 — 200 and an empty completion in 67.97s24 unclassified name(s) went unprobed against the budget; they will be picked up on the next run.
Appended to
profiles/rcc.toml:ling-3.0-flash-fin-freePut back in the picker, answering again:
nemotron-3.5-lightning-free