0.5.44 - audit: refresh all 20 providers (257 models)

- nvidia(+7), github-models(+20), openrouter(+10), qwen(+10), ollama-cloud(+10), llm7(+6), scaleway(+4), mistral(+2), cloudflare(+1), cerebras(+1), codestral(+1), zai(+1)
- removed deprecated: step-3.5-flash, kimi-k2.5, mistral-7b-v0.2, owl-alpha, magistral-1.2, routeway minimax-m2/mistral-nemo, ollama 7 locked
- ctx/sweScore/ID fixes across cerebras, nvidia, github-models, qwen, novita, zai
- audit_state.json fingerprints refreshed for all 20 providers
- test/test.js: updated stale hard-coded model IDs (glm-5.1 -> glm-5.2)

Author: vava-nessa

audit_state.json

@@ -1,81 +1,106 @@
 {
   "_meta": {
-    "totalModels": 157,
-    "lastFullAudit": "2026-06-10"
+    "totalModels": 257,
+    "lastFullAudit": "2026-07-08"
   },
   "nvidia": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "cde1331268a4d3686f34297a4487e92b",
-    "modelCount": 27
+    "lastAudited": "2026-07-08",
+    "fingerprint": "1a022776debc080e6468683032e60947",
+    "modelCount": 31
   },
   "groq": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "dc41cb7450c0b5a97ae5b4c0366656a3",
-    "modelCount": 8
+    "lastAudited": "2026-07-08",
+    "fingerprint": "e065a098a7d02fe6e3ac093c82f39768",
+    "modelCount": 9
   },
   "cerebras": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "36017621a884dd553c73c34757309eaf",
-    "modelCount": 2
+    "lastAudited": "2026-07-08",
+    "fingerprint": "13f81ad23020f6bfff023425b18910fc",
+    "modelCount": 3
   },
   "googleai": {
-    "lastAudited": "2026-06-10",
+    "lastAudited": "2026-07-08",
     "fingerprint": "7c1853c3e20ec800af5798ac0abbc4ca",
     "modelCount": 7
   },
   "github-models": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "073d0cc1aeebaa2cd9d9e58f74e613ae",
-    "modelCount": 15
+    "lastAudited": "2026-07-08",
+    "fingerprint": "5742be2a908c74163d786bda89437958",
+    "modelCount": 35
   },
   "mistral": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "f4776050698087893e6c513f9bcd5932",
-    "modelCount": 5
+    "lastAudited": "2026-07-08",
+    "fingerprint": "8e07fa53b93649b60e4336c81f65cdf5",
+    "modelCount": 7
   },
   "cloudflare": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "f411667b29f00dda92b58537dde8081f",
-    "modelCount": 16
+    "lastAudited": "2026-07-08",
+    "fingerprint": "0edcb0eda30fd1088923cac8eaf00ac9",
+    "modelCount": 17
   },
   "openrouter": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "b02cd17e8b92846ffb716ec86e70dcdf",
-    "modelCount": 24
+    "lastAudited": "2026-07-08",
+    "fingerprint": "ad889216d8c715a28f42706d65da9550",
+    "modelCount": 25
   },
   "sambanova": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "d769460cb4ba340408d26271125bb94e",
-    "modelCount": 7
+    "lastAudited": "2026-07-08",
+    "fingerprint": "078169a8afab2f63a42e74212832f5a4",
+    "modelCount": 6
   },
   "ovhcloud": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "20ab6894a702778f44f0b772a30103a1",
-    "modelCount": 10
+    "lastAudited": "2026-07-08",
+    "fingerprint": "97a038a441e3601abd5faf773836c4e4",
+    "modelCount": 14
   },
   "codestral": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "5e8ca2462d78998441463382957eb963",
-    "modelCount": 1
+    "lastAudited": "2026-07-08",
+    "fingerprint": "aa88453acea900e1d6cb0ccaaf68e375",
+    "modelCount": 2
   },
   "zai": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "bac9274515e6a27920cbad47cf94edb3",
-    "modelCount": 2
+    "lastAudited": "2026-07-08",
+    "fingerprint": "9810e87090ca37044fab2dd9ba76c22e",
+    "modelCount": 3
   },
   "scaleway": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "6c1306c1804eebb73bad4e026ec1065c",
-    "modelCount": 10
+    "lastAudited": "2026-07-08",
+    "fingerprint": "acbdc795b98c778129e9cabdd0d04de1",
+    "modelCount": 15
   },
   "qwen": {
-    "lastAudited": "2026-06-10",
-    "fingerprint": "84abb56ab959de853ff0a53fde0668ea",
-    "modelCount": 11
+    "lastAudited": "2026-07-08",
+    "fingerprint": "08ab14efe65a3111c6083c5325381fad",
+    "modelCount": 21
   },
   "opencode-zen": {
-    "lastAudited": "2026-06-01",
-    "fingerprint": "12f6f6de4460c6708189e0f45bc0cc3f",
+    "lastAudited": "2026-07-08",
+    "fingerprint": "02f87ba135c0598a9c6c11b2f58223d7",
     "modelCount": 5
+  },
+  "kilo": {
+    "lastAudited": "2026-07-08",
+    "modelCount": 1,
+    "fingerprint": "d5017bb2e942233d2dbf23a7e1411730"
+  },
+  "llm7": {
+    "lastAudited": "2026-07-08",
+    "modelCount": 12,
+    "fingerprint": "cea99f4304572742e80f464c980fa817"
+  },
+  "routeway": {
+    "lastAudited": "2026-07-08",
+    "modelCount": 13,
+    "fingerprint": "c3f9c4331e702ed92747b1903c3b1de0"
+  },
+  "novita": {
+    "lastAudited": "2026-07-08",
+    "modelCount": 4,
+    "fingerprint": "ae66741895547f807c31def61e3ceacd"
+  },
+  "ollama-cloud": {
+    "lastAudited": "2026-07-08",
+    "modelCount": 27,
+    "fingerprint": "a7e83162051114e8954c33e6a25848b5"
   }
 }

changelog/v0.5.44.md

@@ -0,0 +1,30 @@
+# Changelog v0.5.44 - 2026-07-08
+
+### Added
+- **Provider catalog audit (all 20 providers)** — refreshed every provider against live official docs/endpoints via the `update_models` skill.
+- **NVIDIA NIM**: added Qwen3 Coder 480B, Mistral Nemotron, Llama 3.3 Nemotron Super 49B v1.5, DeepSeek V3.2, Qwen2.5 Coder 32B, Magistral Small 2506, Nemotron 3 Nano, Llama 4 Scout (A+ / 10M ctx); GLM-5.1 → GLM-5.2.
+- **GitHub Models**: added GPT-5 / GPT-5 Mini / GPT-5 Nano / GPT-5 Chat, GPT-4o / GPT-4o Mini, o3 / o4-mini / o3-mini / o1 / o1-mini / o1-preview, DeepSeek-R1 / R1-0528, Cohere Command A, Phi-4 family (20 models).
+- **Cerebras**: added Gemma 4 31B.
+- **Mistral**: added Ministral 3 family (14B / 8B / 3B); Magistral Medium 1.2 retired.
+- **Cloudflare**: added QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, Llama 3.1 8B Instruct (Fast); removed deprecated Kimi K2.5 and Mistral 7B v0.2.
+- **OpenRouter**: added Tencent Hy3, Qwen3 Coder, Poolside Laguna XS 2.1, Llama 3.3 70B, Hermes 3 405B, Qwen3 Next 80B, Llama 3.2 3B, Dolphin Mistral 24B, Nemotron 3.5 Content Safety, LFM 2.5 1.2B (instruct + thinking); removed Owl Alpha; renamed Nemotron Nano 30B → Nemotron 3 Nano 30B.
+- **Codestral**: added Codestral 2.
+- **Z.ai**: added GLM-4.6V-Flash; GLM-4.7-Flash ctx 200k → 203k.
+- **Scaleway**: added GLM 5.2, Mistral Medium 3.5 128B, Gemma 4 26B MoE, Pixtral 12B; dropped `mistral/` prefix on Mistral Large 675B id.
+- **Qwen**: added Qwen3.7 Plus, Qwen3.6 Max Preview, Qwen3 Coder 480B, Qwen3.5 397B/122B/35B/27B, Qwen3 Next 80B (thinking + instruct), Qwen3 30B; Qwen3 235B & Qwen3 32B ctx corrected 256k → 128k.
+- **LLM7**: added Claude Opus 4.8 / Sonnet 5 / Fable 5, GPT-5.5 / GPT-5.4 / GPT-5.4-mini, GLM 5.2, MiniMax M2.7; removed Qwen3 235B & Mistral Small 3.2; ctx fixes on DeepSeek V4 Flash (1M), Kimi K2.6 (240k), Devstral Small 2 (255k).
+- **Ollama Cloud**: removed 7 paid/locked models (MiniMax M2.7, GLM-5.1, Kimi K2.6, DeepSeek V4 Pro/Flash, Qwen3.5 397B, Mistral Large 3); added 17 free-tier models (Gemma 3 4B/12B/27B, MiniMax M2/M2.1/M2.5, Ministral 3 3B/8B/14B, GLM 4.6, Cogito 2.1 671B, Devstral Small 2 24B, Nemotron 3 Nano 30B, Qwen3 Next 80B, Qwen3 VL 235B + instruct, RNJ 1 8B); ctx fixes on Devstral 2, Nemotron 3 Ultra/Super, GLM-4.7, MiniMax M3.
+- **Novita**: corrected Qwen3.6 Plus SWE score (78.8%) and MiniMax M2 HER ctx (66k).
+- **Routeway**: removed MiniMax M2 and Mistral Nemo free tiers.
+
+### Fixed
+- **Cerebras**: corrected both model context windows from 8k → 128k.
+- **GitHub Models**: Llama 4 Scout ctx 1M → 10M.
+- **NVIDIA NIM**: Kimi K2.6 ctx 256k → 262k; Nemotron 3 Nano 30B ctx 128k → 1M.
+
+### Changed
+- **audit_state.json** regenerated for all 20 providers (total catalog: 257 models, up from 157).
+- Catalog arrays now grouped by tier with inline tier comments for easier review.
+
+### Notes
+- Low/medium-confidence sources (Ollama Cloud third-party probe, Routeway chimera/umbra, LLM7 guessed tiers, Novita free-status) were applied as-is per request; verify before relying on them in production.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.43",
+  "version": "0.5.44",
   "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.",
   "keywords": [
     "nvidia",