fix(docs): deepseek-v4-flash hit NVIDIA EOL — 70 chat / 92 total / 5 free - #43
Merged
Merged
Conversation
…92 total / 5 free NVIDIA published end-of-life for deepseek-ai/deepseek-v4-flash (410 Gone, --real probe both passes, 2026-08-12; prod [ALERT][free-model-dead]). The model is hidden + redirected in the gateway, so every count claim moves: 70 chat / 92 total / 5 free. - 71 LLMs/models -> 70 across the tree - 94 AI models -> 92 (NOTE: reconciles the #41 seedance bump; when blockrun PR #366 lands the total becomes 93 and the guard will force the one-line follow-up) - benchmarks eco SIMPLE tier repriced on nvidia/step-3.7-flash (free, so the 98% eco figure is unchanged) - xrpl + models.md free tables drop the dead model
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
NVIDIA published EOL (410 Gone, both
--realprobe passes, 2026-08-12) for the freenvidia/deepseek-v4-flash— prod fired[ALERT][free-model-dead] kind=gone. Companion to the blockrun-web PR that hides/seeds/redirects the model.71 LLMs/models→ 70,94 AI models→ 92 (reconciles fix(docs): catalog is 94 models after seedance-2.0-mini #41; blockrun PR #366 will move totals to 93 when it lands — its guard will catch the one-liner)nvidia/step-3.7-flash(free → the 98% figure is unchanged)🤖 Generated with Claude Code