free-coding-models 0.5.45 → 0.5.46
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
# Changelog v0.5.46 - 2026-07-08
|
|
2
|
+
|
|
3
|
+
### Fixed
|
|
4
|
+
- **LLM7 catalog corrected against live `/v1/models` API.** The previous audit had added several models that are NOT free on LLM7. The live API shows that of LLM7's 12 models, only 2 are on the `turbo` (free, `noKeyNeeded`) tier; everything else — including the `claude-*` (Fable 5, Opus 4.8, Sonnet 5), `gpt-5.4` / `gpt-5.4-mini` / `gpt-5.5`, `glm-5.2`, `kimi-k2.6`, `deepseek-v4-flash`, and `minimax-m2.7` entries — are `pro` (usage-based paid) and were incorrectly listed as free.
|
|
5
|
+
- **Removed 10 non-free (pro) models from LLM7**, keeping only the two genuinely-free `turbo` models: `devstral-small-2:24b` (S / 68.0%) and `codestral-latest` (A / 40.0%). Total catalog: 257 → 247 models.
|
|
6
|
+
- Removed the `1.05M` context-window entries (gpt-5.5 / gpt-5.4) that were causing alignment drift; no `1.05M` remains in the catalog.
|
|
7
|
+
|
|
8
|
+
### Notes
|
|
9
|
+
- LLM7's free (`turbo`) tier now has only 2 coding models. The `llm7` provider remains `noKeyNeeded: true` and should only surface free models per the source-header rule ("Pro-tagged models from /v1/models are intentionally excluded").
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "free-coding-models",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.46",
|
|
4
4
|
"description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"nvidia",
|
package/sources.js
CHANGED
|
@@ -404,20 +404,10 @@ export const kilo = [
|
|
|
404
404
|
// 📖 Free unauthenticated tier works with tight shared limits; optional free token at https://token.llm7.io
|
|
405
405
|
// 📖 Pro-tagged models from /v1/models are intentionally excluded.
|
|
406
406
|
export const llm7 = [
|
|
407
|
-
//
|
|
408
|
-
|
|
409
|
-
['kimi-k2.6', 'Kimi K2.6', 'S+', '80.2%', '240k'],
|
|
410
|
-
['claude-opus-4-8', 'Claude Opus 4.8', 'S+', '88.6%', '1M'],
|
|
411
|
-
['claude-sonnet-5', 'Claude Sonnet 5', 'S+', '-', '1M'],
|
|
412
|
-
['claude-fable-5', 'Claude Fable 5', 'S+', '95.0%', '1M'],
|
|
413
|
-
['gpt-5.5', 'GPT-5.5', 'S+', '88.7%', '1.05M'],
|
|
414
|
-
['gpt-5.4', 'GPT-5.4', 'S+', '80.0%', '1.05M'],
|
|
415
|
-
['glm-5.2', 'GLM 5.2', 'S+', '82.8%', '1M'],
|
|
416
|
-
// ── A tier — SWE-bench Verified 40–50% ──
|
|
407
|
+
// 📖 LLM7 live /v1/models: only `turbo` tier is free (noKeyNeeded). All `pro` models are usage-based paid.
|
|
408
|
+
// ── S tier — SWE-bench Verified 60–70% ──
|
|
417
409
|
['devstral-small-2:24b', 'Devstral Small 2', 'S', '68.0%', '255k'],
|
|
418
|
-
|
|
419
|
-
['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '180k'],
|
|
420
|
-
// ── B+ tier — SWE-bench Verified 30–35% ──
|
|
410
|
+
// ── A tier — SWE-bench Verified 40–50% ──
|
|
421
411
|
['codestral-latest', 'Codestral Latest', 'A', '40.0%', '32k'],
|
|
422
412
|
]
|
|
423
413
|
|