free-coding-models 0.5.96 → 0.5.98

package/README.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <strong>Find the fastest free coding model in seconds.</strong><br>
-  Live latency, stability and verdicts for 259 models from 25 free AI providers, then install the one you pick straight into your favorite coding tool.<br><br>
+  Live latency, stability and verdicts for 253 models from 25 free AI providers, then install the one you pick straight into your favorite coding tool.<br><br>
   <strong>Works with:</strong> OpenCode CLI / Desktop / WebUI, OpenClaw, Crush, Goose, Aider, Kilo CLI, Qwen Code, OpenHands, Amp, Hermes, Continue, Cline, Xcode, Pi, ZCode, ForgeCode, Copilot, jcode, Caveman Code and more.
 </p>
 
@@ -35,7 +35,7 @@ free-coding-models
 
 ## 💡 Why this tool?
 
-There is a large catalog of free and free-limited coding models (**25 providers / 259 live models**, generated from [`sources.js`](./sources.js)). Which one is fastest *right now*? Which one is actually stable, versus just lucky on the last ping?
+There is a large catalog of free and free-limited coding models (**25 providers / 253 live models**, generated from [`sources.js`](./sources.js)). Which one is fastest *right now*? Which one is actually stable, versus just lucky on the last ping?
 
 `free-coding-models` (FCM) answers that by pinging every model in parallel, showing live latency, and computing a **live Stability Score (0-100)** combining p95 latency, jitter, spike rate and uptime. Average latency alone is misleading: a model that randomly spikes to 6 seconds is not reliable.
 
@@ -87,18 +87,18 @@ free-coding-models --fiable              # print the single most reliable model
 
 ## 🟢 Providers
 
-**25 active providers / 259 live models**, sorted by live model count. Top 8:
+**25 active providers / 253 live models**, sorted by live model count. Top 8:
 
 | Provider | Models | Best tier | Env var |
 |----------|--------|-----------|---------|
-| [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 29 | S+ | `DASHSCOPE_API_KEY` |
-| [Kilo](https://kilo.ai) | 21 | S+ | `KILO_API_KEY` |
-| [OpenRouter](https://openrouter.ai/keys) | 21 | S+ | `OPENROUTER_API_KEY` |
-| [Pollinations AI](https://enter.pollinations.ai) | 21 | S+ | `POLLINATIONS_API_KEY` |
-| [Ollama Cloud](https://ollama.com/settings/keys) | 20 | S+ | `OLLAMA_API_KEY` |
-| [Cloudflare AI](https://dash.cloudflare.com) | 15 | S | `CLOUDFLARE_API_TOKEN` |
-| [OVHcloud AI](https://endpoints.ai.cloud.ovh.net) | 13 | S+ | `OVH_AI_ENDPOINTS_ACCESS_TOKEN` |
-| [NVIDIA NIM](https://build.nvidia.com) | 12 | S+ | `NVIDIA_API_KEY` |
+| [Pollinations AI](https://enter.pollinations.ai) | 24 | S+ | `POLLINATIONS_API_KEY` |
+| [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 22 | S+ | `DASHSCOPE_API_KEY` |
+| [onomeo](https://onomeo.com/dashboard) | 19 | S+ | `ONOMEO_API_KEY` |
+| [Ollama Cloud](https://ollama.com/settings/keys) | 18 | S+ | `OLLAMA_API_KEY` |
+| [OpenRouter](https://openrouter.ai/keys) | 16 | S+ | `OPENROUTER_API_KEY` |
+| [Kilo](https://kilo.ai) | 15 | S+ | `KILO_API_KEY` |
+| [OVHcloud AI](https://endpoints.ai.cloud.ovh.net) | 14 | S+ | `OVH_AI_ENDPOINTS_ACCESS_TOKEN` |
+| [NVIDIA NIM](https://build.nvidia.com) | 13 | S+ | `NVIDIA_API_KEY` |
 
 > 🧾 **What "free" means here:** free is a property of the *(provider, model)* pair, never of the provider as a whole. A row is listed only when that exact model id costs $0 to call through that provider (permanent free tier, `:free` variant, or free plan), verified live at audit time. The same open-weights model can be free on one host and paid on another - paid siblings are deliberately excluded. Full breakdown and badge legend: [`docs/providers.md`](./docs/providers.md).
 

package/changelog/v0.5.97.md

@@ -0,0 +1,24 @@
+### Added
+
+- 📡 **Full 25-provider audit, 2 researchers at a time: 265 → 271 live models.** Every provider verified against its live API or official docs on 2026-09-29.
+- **onomeo free pool exploded to 33 models**: Gemini 3.8/3.7/3.5 Flash, GLM 4.5/4.6V/4.7 Flash and Ministral 3 14B all joined the free pool this week (maintainer-confirmed catalog).
+- **Novita free tier is back**: Qwen3.6 Plus and Qwen3.5 Plus (1M ctx, S+), Ling 3.1 Flash and dev/glm46 are zero-price again after the August dry spell.
+- NVIDIA NIM: DeepSeek V4.1 Flash (1M ctx, 552B MoE agentic coder), Kimi K2.6 (256k), Nemotron Nano 3 30B and Codestral 22B re-verified live.
+- LLM7: DeepSeek V4 Flash 0731 (400k ctx, reasoning + tools) verified answering with no key at all.
+- OpenRouter: Space Bunny Alpha (anonymous stealth, 1M ctx) and the openrouter/free meta-router.
+- OVHcloud: Qwen3-Coder-30B-A3B and Mistral Small 3.2 live on the router even though the marketing page hides them.
+- ⚙️ **Env variable placeholders in the config file (issue #196)**: any `apiKeys` value can now be `"${MY_VAR}"` and is resolved from the environment at read time. The file on disk keeps the placeholder so secrets never land on disk - perfect for Docker `env_file` setups. The shell env-file generator skips placeholder entries instead of exporting a literal that would clobber your real variable.
+
+### Changed
+
+- 🪦 **6 DashScope models flagged deprecated, shutdown 2026-10-10** per official Alibaba notices: qwen3-coder-plus, qwen3-coder-next, qwen3-coder-480b, qwen3-coder-30b, qwen3.6-max-preview and qwen3-vl-flash. They still serve until then; qwen3.7-plus/3.7-max are the replacements.
+- OrcaRouter quota strings now reflect reality: 5 $0 models + the router, 10 req/min, 50 req/day.
+- Docs provider table regenerated against the shipped catalog.
+
+### Fixed
+
+- 🐛 **CORS in Docker finally tamed (issue #198)**: `FCM_ALLOWED_ORIGINS="*"` now works. The list used to be exact-match only, so the `*` entry was silently ignored and cross-machine browser tabs failed CORS checks. Host-header DNS-rebinding protection stays on.
+- Removed 13 dead or quietly-paid models: mistral-nemotron (EOL 09-28), kimi-k2-thinking (EOL 05-12), Mistral Large 3 (403 paid-tier-only on a free key), Z.ai GLM-5.3 + FlashX (paid-only), Zen DeepSeek-V4-Flash-Free (upstream dead) and Muse Spark 1.2 (de-promoted), the ling-3.0-flash-fin `:free` variants on OpenRouter/Kilo, 2 paid Ling models on Novita, and the OrcaRouter fusion trio, which bills the sum of its paid frontier panel legs despite reporting $0.
+- Context windows corrected against live data: GLM-5.3 on NVIDIA 200k → 1M, muse-glimmer and gpt-oss-20b 128k → 131k, Zen space-bunny and longcat 200k → 1M, Pollinations nova-2-lite → nova-2-lite-v1 rename, Nex N2.5 pair ctx filled at 256k.
+- Kimi K3 on Ollama Cloud now shows its 76.8% SWE-bench Verified score.
+- onomeo provider text synced with the site's current model (PR #201, thanks @Owaid0723666).

package/changelog/v0.5.98.md

@@ -0,0 +1,39 @@
+# Changelog v0.5.98 - 2026-10-10
+
+Full 25-provider audit against live provider APIs, official catalogs and deprecation notices. The catalog goes from 271 to 253 models: 46 dead or now-paid models removed, 28 fresh free coding models added, 9 metadata fixes.
+
+### Added
+
+- **Step 5 Preview lands on 4 gateways**: Kilo (`stepfun/step-5-preview-free`, S, 1M ctx), OpenCode Zen (`step-5-preview-free`), llm7 and Pollinations - the StepFun flagship preview is this week's big free-model rollout.
+- **Ling 3.1 Flash (560B-A25B MoE) replaces the retired Ling 3.0 :free slots** on OpenRouter ($0/$0), Kilo, OpenCode Zen, Requesty, Novita and Vercel AI Gateway (`ling-3.1-flash-free`).
+- **Glyph Cluster, the new free stealth coding model**, takes the stealth slot on Kilo and Vercel AI Gateway (Pixel Canary rotated out).
+- **llm7 rebuilds its free tier**: + GLM-5.3-Flash (400k ctx, turbo tier), + Kimi K2.7 Code, + Kimi K2.6, + GPT-OSS 20B, + Nemotron 3 Nano 30B (1M ctx) - the catalog grows from 4 to 8 models.
+- **Novita reshuffles around the Qwen3.8 generation**: + GLM-5.3-Flash (1M ctx), + Qwen3.8 Flash (1M ctx), + Ling 3.0 Flash, + GLM-4.7-Flash, + MiniMax M2.7.
+- **Pollinations**: + OpenAI GPT-6.1 Sol (S+, 1M ctx), + xAI Grok 4.7 (S, 500k ctx), + StepFun Step 5 Preview (A+, 1M ctx).
+- **onomeo**: + Gemini 3.6 Flash (S+, 1M ctx) and + Hunyuan 4 Preview (1M ctx), replacing the removed Hunyuan 3 slot.
+- **Mistral La Plateforme**: + Mistral Vibe CLI (new free coding model) and + Leanstral 1.5.1 (successor of Leanstral 1.5).
+- **Ollama Cloud**: + Mistral Large 4 (1.05T MoE, 1M ctx, ~Oct 4 release).
+- **OpenRouter**: + Apodex 1.1 Mini (`:free`, 262k ctx).
+
+### Changed
+
+- **qwen (Alibaba DashScope): 5 models retired exactly today, 2026-10-10**, as predicted by the in-file deprecation notices: qwen3.6-max-preview, qwen3-coder-plus, qwen3-coder-next, qwen3-coder-480b-a35b-instruct and qwen3-coder-30b-a3b-instruct (notices 1949/1950), plus qwen3-vl-flash. Also dropped the phantom qwen3.8-flash-next (404 detail page, never existed in the product index). 29 -> 22 models.
+- **onomeo: 16 of 33 models removed** following the provider's own removed list, and mirrored ids renamed to first-party ones (`openai/gpt-oss-20b` -> `gpt-oss-20b`, `z-ai/glm-5.3-flash-free` -> `glm-5.3-flash`, `meta/muse-glimmer-30b` -> `muse-glimmer-30b`). 5 remaining models are flagged as upstream-paused.
+- **nvidia: the 3 models re-added on 2026-09-29 are ghost catalog entries again** (page 404 + absent from the hosted list): Kimi K2.6, Nemotron Nano 3 30B, Codestral 22B removed; 16 -> 13 models.
+- **sambanova: MiniMax M2.7 and M3 went paid-only** - the official Free Tier table now covers exactly 5 models, the MiniMax pair needs a linked payment method (Developer Tier). 7 -> 5 models.
+- **kilo: hard free-tier rotation** - qwen3.8-27b:free, step-3.7:free, ling-3.0-flash-sante:free and space-bunny-alpha gone; note: paid Poolside Laguna variants retire Oct 31, the free ones may follow.
+- **openrouter**: qwen3.8-27b:free deleted from the live catalog, ling-3.0-flash-sante went paid, stealth/space-bunny-alpha rotated out.
+- **novita**: the Qwen3.5/3.6 Plus tier was killed in favor of Qwen3.8 (2 removals).
+- **ovhcloud**: Qwen3-Coder-30B is dead again (model_not_found on live probe). Warning from the audit: OVH now bills most text models per token - only a handful stay tagged Free on the catalog page.
+- **Moderation classifiers cleaned out of the coding catalog**: Nemotron 3.5 Content Safety removed from OpenRouter, Kilo and Requesty (guardrail model, not coding-capable).
+- README counts and the Top 8 provider table refreshed; `docs/providers.md` regenerated from `sources.js`.
+
+### Fixed
+
+- qwen omni context windows were wrong: qwen3.5-omni-plus 32k -> 256k, qwen3.8-omni-flash 32k -> 1M (official model pages).
+- onomeo: gpt-oss-20b and muse-glimmer-30b ctx 128k -> 131k, minimax-m2.7 ctx 200k -> 205k (live catalog).
+- kilo: openrouter/free ctx dropped (the live gateway no longer publishes a context length for the router).
+
+### Deliberately NOT added (audit transparency)
+
+15 researcher-reported additions were skipped because they reversed verdicts already recorded in `sources.js` from earlier audits, with no stronger evidence: the 6 "free again" SiliconFlow small models (API needs a paid-check key to verify), 4 Pollinations models flagged "paid Pollen" on 2026-09-26/28 (the issue #190 trap: they return HTTP 200 with an embedded credits error, and this audit did not sniff completion bodies), QwQ 32B + R1-Distill on Cloudflare (supersession decision re-confirmed 2026-09-29), the twice-removed Mistral 7B v0.3 / Nemo 12B on OVHcloud, and gemini-3.1-pro-preview on Google AI (excluded twice as paid-only). All are documented in `sources.js` comments for the next audit to re-verify with live keys.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.96",
+  "version": "0.5.98",
   "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",