vava-nessa/free-coding-models v0.5.95 on GitHub

🌐 Pollinations: Claude Opus 5 (S+, 1M), Claude Sonnet 5 (S, 1M), LongCat 2.0 (A, 1M) and DeepSeek V4.1 Flash (A+, 1M) are now reachable free via Pollen credits. Flagged gemini-3.1-pro-preview as reporting 'down' on the live catalog, re-verify next audit.
🔀 OrcaRouter: the fusion family (fusion S, fusion-mini A+, fusion-flash B+) now reports $0 with real context lengths, so all three are listed.
🇫🇷 Mistral: Mistral Large 3 (mistral-large-2512, S+, 256k) re-added. The 2026-09-16 removal was stale, the 675B MoE flagship is back in the official catalog. Also added Leanstral 1.5 (B, 256k, Lean 4 theorem proving).
⚡ NVIDIA NIM: GLM-5.3-Flash (S+, 1M) verified live on the free integrate API.
🇫🇷 Scaleway: Qwen3.8 27B (A+, 256k) added to the Serverless catalog.
🧩 OpenCode Zen: MiMo-V2.6 Flash Free (S+, 200k) new free promo model on the live Zen endpoint.
🧱 Kilo: Nemotron 3.5 Content Safety (C, 128k) added for breadth, matching OpenRouter/Requesty.
🐉 SiliconFlow: Hunyuan MT 7B (C, 33k) added as the new $0 chat model.

🪦 Novita: bunny, Qwen 3.6 Plus, Qwen 3.5 Plus and GLM 4.6 (dev) all gone paid or delisted. Only the 3 Ling 3.0 Flash variants stay free (time-limited).
🪦 SiliconFlow: DeepSeek R1 0528 Qwen3 8B and Qwen3.5 4B dropped off the official free pricing list.
🪦 Mistral: Magistral Medium officially deprecated upstream 2026-05-22, replacement Mistral Medium 3.5 (already listed).

🔍 Full 24-provider re-audit, live-verified 2026-09-22: 247 → 254 free models. 14 providers confirmed with zero changes (groq, cerebras, googleai, cloudflare, openrouter, sambanova, ovhcloud, codestral, zai, qwen, llm7, routeway, requesty, vercel-gateway, ollama-cloud).
✅ Test updated: NVIDIA static-head expectation now reflects the new catalog order.