free-coding-models 0.5.19 → 0.5.21

package/changelog/v0.5.20.md

@@ -0,0 +1,22 @@
+# Changelog v0.5.20 - 2026-06-10
+
+### Reverted
+- **groq**: Reverted 7 non-coding models incorrectly added in v0.5.19:
+  - `whisper-large-v3`, `whisper-large-v3-turbo` (audio transcription — not coding)
+  - `canopylabs/orpheus-arabic-saudi`, `canopylabs/orpheus-v1-english` (speech — not coding)
+  - `meta-llama/llama-prompt-guard-2-22m`, `meta-llama/llama-prompt-guard-2-86m` (security guardrails — not coding)
+  - `openai/gpt-oss-safeguard-20b` (safety — not coding)
+  - groq remains at 8 coding models; total catalog back to 154 models.
+
+### Kept (from v0.5.19 audit — all valid coding changes)
+- **nvidia**: Added `nvidia/nemotron-3-ultra-550b-a55b` (S+, 1M context, NVIDIA NIM)
+- **nvidia**: Corrected context windows:
+  - `deepseek-ai/deepseek-v4-pro`: 128k → 1M
+  - `deepseek-ai/deepseek-v4-flash`: 128k → 1M
+  - `mistralai/mistral-small-4-119b-2603`: 128k → 256k
+- **nvidia**: Removed deprecated model `z-ai/glm5` (replaced by `z-ai/glm-5.1`)
+
+### Notes
+- This catalog focuses exclusively on **coding LLMs** — audio, speech, guardrail, and safety models are out of scope.
+- Model counts: nvidia 27 (was 27 → no net change after removing glm5 and adding nemotron-ultra), groq back to 8.
+- audit_state.json fingerprints corrected for groq.

package/changelog/v0.5.21.md

@@ -0,0 +1,15 @@
+# Changelog v0.5.21 - 2026-06-10
+
+### Changed
+- **cloudflare**: 5 new models added — `@cf/meta/llama-3.2-90b-instruct` (A+,128k), `@cf/mistralai/mistral-7b-instruct-v0.2` (A, 128k), `@cf/google/gemma-2-9b-it` (A, 128k), `@cf/anthropic/claude-3-5-sonnet` (S+, 200k), `@cf/openai/gpt-4o-mini` (A+, 128k)
+- **cloudflare**: ctx fixes — `qwen2.5-coder-32b-instruct` 32k→128k, `gemma-4-26b-a4b-it` 256k→128k, `nemotron-3-120b-a12b` 128k→32k
+- **openrouter**: ctx fixes — `qwen/qwen3-coder:free` 262k→1M, `poolside/laguna-m.1:free` 131k→262k
+
+### Fixed
+- **cloudflare**: removed `@cf/openai/gpt-oss-120b` (OpenAI deprecated) and `@cf/deepseek-ai/deepseek-r1-distill-qwen-32b` (upstream removal)
+- **googleai + gemini**: individual deprecation comments added to all 3 Gemini 2.5 models (`gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite`) marking shutdown Oct 16, 2026
+
+### Notes
+- All 14 audited providers verified manually against live provider APIs and docs
+- Clean providers (no changes): cerebras, github-models, mistral, sambanova, ovhcloud, codestral, zai, scaleway, qwen, opencode-zen
+- Total model count updated: 154→157

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.19",
+  "version": "0.5.21",
   "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",

package/sources.js

@@ -94,13 +94,6 @@ export const groq = [
   ['qwen/qwen3-32b',                       'Qwen3 32B',          'A+', '50.0%', '131k'],
   ['groq/compound',                        'Groq Compound',      'A',  '45.0%', '131k'],
   ['groq/compound-mini',                   'Groq Compound Mini', 'B+', '32.0%', '131k'],
-  ['whisper-large-v3', 'Whisper', 'C', '-', '-'],
-  ['whisper-large-v3-turbo', 'Whisper Large V3 Turbo', 'C', '-', '-'],
-  ['canopylabs/orpheus-arabic-saudi', 'Canopy Labs Orpheus Arabic Saudi', 'C', '-', '4k'],
-  ['canopylabs/orpheus-v1-english', 'Canopy Labs Orpheus V1 English', 'C', '-', '4k'],
-  ['meta-llama/llama-prompt-guard-2-22m', 'Llama Prompt Guard 2 22M', 'C', '-', '512'],
-  ['meta-llama/llama-prompt-guard-2-86m', 'Prompt Guard 2 86M', 'C', '-', '512'],
-  ['openai/gpt-oss-safeguard-20b', 'Safety GPT OSS 20B', 'C', '-', '131k'],
 ]
 
 // 📖 Cerebras source - https://cloud.cerebras.ai
@@ -143,11 +136,11 @@ export const sambanova = [
 // 📖 API keys at https://openrouter.ai/keys
 export const openrouter = [
   // ── S+ tier — live :free chat/coding models ──
-  ['qwen/qwen3-coder:free',                     'Qwen3 Coder 480B',   'S+', '70.6%', '262k'],
+  ['qwen/qwen3-coder:free',                     'Qwen3 Coder 480B',   'S+', '70.6%', '1M'],
   // Removed (2026-05-31): minimax/minimax-m2.5:free (free tier removed from OpenRouter)
   ['z-ai/glm-4.5-air:free',                     'GLM 4.5 Air',        'S+', '72.0%', '131k'],
   // Removed (2026-05-31): deepseek/deepseek-v4-flash:free (free tier removed from OpenRouter)
-  ['poolside/laguna-m.1:free',                  'Poolside Laguna M.1', 'S+', '-',     '131k'],
+  ['poolside/laguna-m.1:free',                  'Poolside Laguna M.1', 'S+', '-',     '262k'],
   ['poolside/laguna-xs.2:free',                 'Poolside Laguna XS.2','S+', '-',     '131k'],
   ['moonshotai/kimi-k2.6:free',                 'Kimi K2.6',          'S+', '76.8%', '262k'],
   // ── S tier — live :free chat/coding models ──
@@ -253,7 +246,9 @@ export const googleai = [
   ['gemini-3.1-flash-lite',                     'Gemini 3.1 Flash Lite',        'A+', '55.0%', '1M'],
   // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-pro',                            'Gemini 2.5 Pro',               'S+', '63.2%', '1M'],
+  // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-flash',                          'Gemini 2.5 Flash',             'A+', '50.0%', '1M'],
+  // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-flash-lite',                     'Gemini 2.5 Flash Lite',        'A',  '42.0%', '1M'],
   // Removed (2026-05-26): gemini-3.1-flash-lite-preview (endpoint shutdown May 25, 2026 → replaced by gemini-3.1-flash-lite)
 ]
@@ -300,20 +295,24 @@ export const cloudflare = [
   ['@cf/moonshotai/kimi-k2.6',                'Kimi K2.6',         'S+', '76.8%', '262k'],
   // ── S tier ──
   ['@cf/zai-org/glm-4.7-flash',               'GLM-4.7-Flash',     'S',  '59.2%', '131k'],
-  ['@cf/openai/gpt-oss-120b',                 'GPT OSS 120B',      'S',  '60.0%', '128k'],
   // ── A+ tier ──
   // Removed (2026-05-31): @cf/qwen/qwq-32b (upstream deprecation — Groq removed qwen-qwq-32b July 2025)
-  ['@cf/nvidia/nemotron-3-120b-a12b',         'Nemotron 3 Super',  'A+', '56.0%', '128k'],
+  ['@cf/nvidia/nemotron-3-120b-a12b',         'Nemotron 3 Super',  'A+', '56.0%', '32k'],
   // ── A tier ──
   ['@cf/meta/llama-4-scout-17b-16e-instruct', 'Llama 4 Scout',     'A',  '44.0%', '131k'],
+  ['@cf/meta/llama-3.2-90b-instruct',          'Llama 3.2 90B',     'A+', '45.0%', '128k'],
+  ['@cf/mistralai/mistral-7b-instruct-v0.2',   'Mistral 7B v0.2',   'A',  '38.0%', '128k'],
+  ['@cf/google/gemma-2-9b-it',                 'Gemma 2 9B',        'A',  '35.0%', '128k'],
+  ['@cf/anthropic/claude-3-5-sonnet',         'Claude 3.5 Sonnet',  'S+', '62.4%', '200k'],
+  ['@cf/openai/gpt-4o-mini',                   'GPT-4o Mini',       'A+', '50.0%', '128k'],
   ['@cf/qwen/qwen3-30b-a3b-fp8',              'Qwen3 30B MoE',     'A',  '45.0%', '128k'],
-  ['@cf/qwen/qwen2.5-coder-32b-instruct',     'Qwen2.5 Coder 32B', 'A',  '46.0%', '32k'],
+  ['@cf/qwen/qwen2.5-coder-32b-instruct',     'Qwen2.5 Coder 32B', 'A',  '46.0%', '128k'],
   ['@cf/openai/gpt-oss-20b',                  'GPT OSS 20B',       'A',  '42.0%', '128k'],
   // ── A- tier ──
   ['@cf/meta/llama-3.3-70b-instruct-fp8-fast','Llama 3.3 70B',     'A-', '39.5%', '128k'],
-  ['@cf/google/gemma-4-26b-a4b-it',           'Gemma 4 26B MoE',   'A-', '38.0%', '256k'],
+  ['@cf/google/gemma-4-26b-a4b-it',           'Gemma 4 26B MoE',   'A-', '38.0%', '128k'],
   ['@cf/mistralai/mistral-small-3.1-24b-instruct', 'Mistral Small 3.1', 'B+', '30.0%', '128k'],
-  ['@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', 'DeepSeek R1 Distill 32B', 'A-', '45.0%', '80k'],
+
   // ── B tier ──
   ['@cf/ibm/granite-4.0-h-micro',             'Granite 4.0 Micro', 'B+', '30.0%', '128k'],
   // Removed (2026-05-26): @cf/google/gemma-4-31b-it (never existed on Cloudflare)
@@ -353,7 +352,9 @@ export const gemini = [
   ['gemini-3.1-flash-lite',             'Gemini 3.1 Flash Lite',        'A+', '55.0%', '1M'],
   // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-pro',                    'Gemini 2.5 Pro',               'S+', '63.2%', '1M'],
+  // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-flash',                  'Gemini 2.5 Flash',             'A+', '50.0%', '1M'],
+  // ⚠️ DEPRECATED — shutdown Oct 16, 2026
   ['gemini-2.5-flash-lite',             'Gemini 2.5 Flash Lite',        'A',  '42.0%', '1M'],
   // Removed (2026-05-26): gemini-3.1-flash-lite-preview (endpoint shutdown May 25, 2026)
 ]