free-coding-models 0.5.19 → 0.5.20
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 +1,22 @@
|
|
|
1
|
+
# Changelog v0.5.20 - 2026-06-10
|
|
2
|
+
|
|
3
|
+
### Reverted
|
|
4
|
+
- **groq**: Reverted 7 non-coding models incorrectly added in v0.5.19:
|
|
5
|
+
- `whisper-large-v3`, `whisper-large-v3-turbo` (audio transcription — not coding)
|
|
6
|
+
- `canopylabs/orpheus-arabic-saudi`, `canopylabs/orpheus-v1-english` (speech — not coding)
|
|
7
|
+
- `meta-llama/llama-prompt-guard-2-22m`, `meta-llama/llama-prompt-guard-2-86m` (security guardrails — not coding)
|
|
8
|
+
- `openai/gpt-oss-safeguard-20b` (safety — not coding)
|
|
9
|
+
- groq remains at 8 coding models; total catalog back to 154 models.
|
|
10
|
+
|
|
11
|
+
### Kept (from v0.5.19 audit — all valid coding changes)
|
|
12
|
+
- **nvidia**: Added `nvidia/nemotron-3-ultra-550b-a55b` (S+, 1M context, NVIDIA NIM)
|
|
13
|
+
- **nvidia**: Corrected context windows:
|
|
14
|
+
- `deepseek-ai/deepseek-v4-pro`: 128k → 1M
|
|
15
|
+
- `deepseek-ai/deepseek-v4-flash`: 128k → 1M
|
|
16
|
+
- `mistralai/mistral-small-4-119b-2603`: 128k → 256k
|
|
17
|
+
- **nvidia**: Removed deprecated model `z-ai/glm5` (replaced by `z-ai/glm-5.1`)
|
|
18
|
+
|
|
19
|
+
### Notes
|
|
20
|
+
- This catalog focuses exclusively on **coding LLMs** — audio, speech, guardrail, and safety models are out of scope.
|
|
21
|
+
- Model counts: nvidia 27 (was 27 → no net change after removing glm5 and adding nemotron-ultra), groq back to 8.
|
|
22
|
+
- audit_state.json fingerprints corrected for groq.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "free-coding-models",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.20",
|
|
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
|
@@ -94,13 +94,6 @@ export const groq = [
|
|
|
94
94
|
['qwen/qwen3-32b', 'Qwen3 32B', 'A+', '50.0%', '131k'],
|
|
95
95
|
['groq/compound', 'Groq Compound', 'A', '45.0%', '131k'],
|
|
96
96
|
['groq/compound-mini', 'Groq Compound Mini', 'B+', '32.0%', '131k'],
|
|
97
|
-
['whisper-large-v3', 'Whisper', 'C', '-', '-'],
|
|
98
|
-
['whisper-large-v3-turbo', 'Whisper Large V3 Turbo', 'C', '-', '-'],
|
|
99
|
-
['canopylabs/orpheus-arabic-saudi', 'Canopy Labs Orpheus Arabic Saudi', 'C', '-', '4k'],
|
|
100
|
-
['canopylabs/orpheus-v1-english', 'Canopy Labs Orpheus V1 English', 'C', '-', '4k'],
|
|
101
|
-
['meta-llama/llama-prompt-guard-2-22m', 'Llama Prompt Guard 2 22M', 'C', '-', '512'],
|
|
102
|
-
['meta-llama/llama-prompt-guard-2-86m', 'Prompt Guard 2 86M', 'C', '-', '512'],
|
|
103
|
-
['openai/gpt-oss-safeguard-20b', 'Safety GPT OSS 20B', 'C', '-', '131k'],
|
|
104
97
|
]
|
|
105
98
|
|
|
106
99
|
// 📖 Cerebras source - https://cloud.cerebras.ai
|