free-coding-models 0.5.80 → 0.5.81

package/README.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <strong>Find the fastest free coding model in seconds</strong><br>
-  Track ~222 models across 20 trusted free or free-limited AI providers in real time, then install the one you pick straight into your favorite coding tool.<br><br>
+  Track a large catalog of free coding models from 20+ trusted AI providers in real time, 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 and more.<br><br>
   <strong>Use Kimi K2, DeepSeek V3/V4, GPT-OSS, Qwen3, MiniMax M3, GLM, Llama 4, Gemma 4, Devstral and more — for free</strong>
 </p>
@@ -15,8 +15,8 @@
   <img src="https://img.shields.io/npm/v/free-coding-models?color=3d6b00&label=npm&logo=npm" alt="npm version" width="200"><br>
   <img src="https://img.shields.io/node/v/free-coding-models?color=3d6b00&logo=node.js" alt="node version" width="200"><br>
   <img src="https://img.shields.io/npm/l/free-coding-models?color=3d6b00" alt="license" width="200"><br>
-  <img src="https://img.shields.io/badge/models-222-3d6b00?logo=nvidia" alt="models count" width="200"><br>
-  <img src="https://img.shields.io/badge/providers-20-1a56db" alt="providers count" width="200">
+  <img src="https://img.shields.io/badge/models-large%20catalog-3d6b00?logo=nvidia" alt="models count" width="200"><br>
+  <img src="https://img.shields.io/badge/providers-20%2B-1a56db" alt="providers count" width="200">
 </p>
 
 ```bash
@@ -25,7 +25,7 @@ free-coding-models
 ```
 
 <p align="center">
-  <sub>Then create a free account on one of the <a href="#-free-ai-providers">20 providers</a> to grab an API key.</sub>
+  <sub>Then create a free account on one of the <a href="#-free-ai-providers">many providers</a> to grab an API key.</sub>
 </p>
 
 <p align="center">
@@ -60,7 +60,7 @@ free-coding-models
 
 ## 💡 Why this tool?
 
-There are **~222 cataloged free or free-limited coding models** across 20 vetted providers. 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 from 20+ vetted providers. 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)**. Average latency alone is misleading — a model that randomly spikes to 6 seconds isn't reliable. The stability score combines **p95 latency** (30%), **jitter/variance** (30%), **spike rate** (20%), and **uptime** (20%) to measure true reliability.
 
@@ -94,7 +94,7 @@ Requires **Node.js 18+**. That's the only prerequisite — FCM has a single runt
 
 ### ② Grab one free API key
 
-FCM tracks ~222 models across 20 providers, but you only need **one key** to start. The fastest sign-ups (no credit card, instant key):
+FCM tracks a large catalog of models from 20+ providers, but you only need **one key** to start. The fastest sign-ups (no credit card, instant key):
 
 - **Groq** → [console.groq.com/keys](https://console.groq.com/keys) — Llama 4, GPT-OSS, blazing fast
 - **Cerebras** → [cloud.cerebras.ai](https://cloud.cerebras.ai) — the lowest latency in the whole catalog
@@ -165,30 +165,35 @@ Once the TUI feels familiar, FCM has three more surfaces — pick the one that m
 
 ## 🟢 Free AI Providers
 
-**~222 coding models** across 20 active providers, ranked by practical free-tier usefulness. Sign up on any one of them to get a key — you only need one to start.
+A large catalog of coding models from 20+ active providers, ranked by practical free-tier usefulness. Sign up on any one of them to get a key — you only need one to start.
 
 | # | Provider | Models | Tier range | Free tier | Env var |
 |---|----------|--------|-----------|-----------|--------|
-| 1 | [NVIDIA NIM](https://build.nvidia.com) | 27 | S+ → C | ~40 RPM (no credit card) | `NVIDIA_API_KEY` |
-| 2 | [Groq](https://console.groq.com/keys) | 8 | S → B | 30 RPM, 1K‑14.4K req/day (no credit card) | `GROQ_API_KEY` |
+| 1 | [NVIDIA NIM](https://build.nvidia.com) | 25 | S+ → C | ~40 RPM (no credit card) | `NVIDIA_API_KEY` |
+| 2 | [Groq](https://console.groq.com/keys) | 5 | S → B | 30 RPM, 1K‑14.4K req/day (no credit card) | `GROQ_API_KEY` |
 | 3 | [Cerebras](https://cloud.cerebras.ai) | 2 | S+ → S | 30 RPM, 1M tokens/day (no credit card) | `CEREBRAS_API_KEY` |
-| 4 | [Google AI Studio](https://aistudio.google.com/apikey) | 7 | S+ → A | Gemini free quotas vary by model/region | `GOOGLE_API_KEY` |
-| 5 | [GitHub Models](https://models.github.ai) | 15 | S+ → C | Quota depends on GitHub/Copilot tier | `GITHUB_TOKEN` |
-| 6 | [Mistral La Plateforme](https://console.mistral.ai/api-keys) | 5 | S+ → A | Experiment plan, free evaluation tier | `MISTRAL_API_KEY` |
-| 7 | [Cloudflare Workers AI](https://dash.cloudflare.com) | 16 | S+ → B | 10K neurons/day, 300 RPM (no credit card) | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` |
-| 8 | [OpenRouter](https://openrouter.ai/keys) | 24 | S+ → C | 50 req/day free, 1K/day with $10 spend | `OPENROUTER_API_KEY` |
-| 9 | [SambaNova](https://cloud.sambanova.ai/apis) | 7 | S+ → B+ | Small developer quota, useful for light usage | `SAMBANOVA_API_KEY` |
-| 10 | [OVHcloud AI Endpoints](https://endpoints.ai.cloud.ovh.net) | 10 | S → B | 2 req/min/IP free, 400 RPM with key | `OVH_AI_ENDPOINTS_ACCESS_TOKEN` |
-| 11 | [Codestral](https://console.mistral.ai/api-keys) | 1 | B+ | 30 RPM, 2K req/day | `MISTRAL_API_KEY` |
-| 12 | [ZAI](https://z.ai) | 2 | S | Free Flash models only | `ZAI_API_KEY` |
-| 13 | [Scaleway](https://console.scaleway.com/iam/api-keys) | 10 | S+ → B | 1M free tokens | `SCALEWAY_API_KEY` |
-| 14 | [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 11 | S+ → A+ | 1M free tokens/model, Singapore, 90 days | `DASHSCOPE_API_KEY` |
-| 15 | [OpenCode Zen](https://opencode.ai/zen) | 5 | S+ → A | Free with OpenCode account | Zen models ✨ |
-| 16 | [Kilo](https://kilo.ai) | 1 | A+ | Free auto-router works without a key | optional `KILO_API_KEY` |
-| 17 | [LLM7](https://llm7.io) | 4 | S+ → B+ | Shared free tier, optional free token | optional `LLM7_API_KEY` |
-| 18 | [Routeway](https://routeway.ai) | 15 | S+ → C | Explicit `:free` zero-price models | `ROUTEWAY_API_KEY` |
-| 19 | [Novita AI](https://novita.ai) | 4 | S+ → S | Only zero-price live chat models included | `NOVITA_API_KEY` |
-| 20 | [Ollama Cloud](https://ollama.com/pricing) | 17 | S+ → A | Free cloud usage with session/weekly limits | `OLLAMA_API_KEY` |
+| 4 | [Google AI Studio](https://aistudio.google.com/apikey) | 10 | S+ → A | Gemini free quotas vary by model/region | `GOOGLE_API_KEY` |
+| 5 | [Mistral La Plateforme](https://console.mistral.ai/api-keys) | 6 | S+ → A | Experiment plan, free evaluation tier | `MISTRAL_API_KEY` |
+| 6 | [Cloudflare Workers AI](https://dash.cloudflare.com) | 19 | S+ → B | 10K neurons/day, 300 RPM (no credit card) | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` |
+| 7 | [OpenRouter](https://openrouter.ai/keys) | 14 | S+ → C | 50 req/day free, 1K/day with $10 spend | `OPENROUTER_API_KEY` |
+| 8 | [SambaNova](https://cloud.sambanova.ai/apis) | 6 | S+ → B+ | Small developer quota, useful for light usage | `SAMBANOVA_API_KEY` |
+| 9 | [OVHcloud AI Endpoints](https://endpoints.ai.cloud.ovh.net) | 10 | S → B | 2 req/min/IP free, 400 RPM with key | `OVH_AI_ENDPOINTS_ACCESS_TOKEN` |
+| 10 | [Codestral](https://console.mistral.ai/api-keys) | 1 | B+ | 30 RPM, 2K req/day | `MISTRAL_API_KEY` |
+| 11 | [ZAI](https://z.ai) | 7 | S | Free Flash models only | `ZAI_API_KEY` |
+| 12 | [Scaleway](https://console.scaleway.com/iam/api-keys) | 15 | S+ → B | 1M free tokens | `SCALEWAY_API_KEY` |
+| 13 | [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 23 | S+ → A+ | 1M free tokens/model, Singapore, 90 days | `DASHSCOPE_API_KEY` |
+| 14 | [OpenCode Zen](https://opencode.ai/zen) | 5 | S+ → A | Free with OpenCode account | Zen models ✨ |
+| 15 | [Kilo](https://kilo.ai) | 2 | A+ | Free auto-router works without a key | optional `KILO_API_KEY` |
+| 16 | [LLM7](https://llm7.io) | 5 | S+ → B+ | Shared free tier, optional free token | optional `LLM7_API_KEY` |
+| 17 | [Routeway](https://routeway.ai) | 10 | S+ → C | Explicit `:free` zero-price models | `ROUTEWAY_API_KEY` |
+| 18 | [Novita AI](https://novita.ai) | 0 | - | No zero-price models currently | `NOVITA_API_KEY` |
+| 19 | [Ollama Cloud](https://ollama.com/pricing) | 17 | S+ → A | Free cloud usage with session/weekly limits | `OLLAMA_API_KEY` |
+| 20 | [Pollinations AI](https://enter.pollinations.ai) ⚠️ experimental | 10 | S+ → B+ | Daily Pollen grants, free tier via Pollen (see note below) | `POLLINATIONS_API_KEY` |
+| 21 | [SiliconFlow](https://cloud.siliconflow.cn/account/ak) | 3 | A → B+ | 3 models @ $0, 1000 RPM (phone SMS required) | `SILICONFLOW_API_KEY` |
+| 22 | [Requesty](https://app.requesty.ai/api-keys) | 12 | S+ → C | 200 req/day free, no card (4x OpenRouter) | `REQUESTY_API_KEY` |
+
+> **Pollinations Pollen, c'est quoi ?** Pollinations ne facture pas en $ mais en **Pollen** (≈ $1). Pas besoin d'acheter : tu recois du Pollen **gratuit chaque jour** selon ton tier seed/flower/nectar via quests (star le repo `pollinations/pollinations` sur GitHub, aider sur un issue). Si ton solde affiche `0.0000` sur `enter.pollinations.ai`, tout `MISS` (prompt non cache) retourne `402 PAYMENT_REQUIRED` ("Insufficient balance ~0.0001 pollen") et le ping affichera `402`. Un `HIT` Cloudflare cache peut encore passer en `200` meme avec 0 Pollen mais ce n'est pas fiable. Verifie ton solde sur `enter.pollinations.ai` -> API Keys, complete une quest et attends le grant quotidien a minuit UTC. **Note : integration Pollinations encore experimentale et non confirmee comme stable, le systeme Pollen peut changer.**
+> **SiliconFlow & Requesty** : integrations verifiees le 2026-08-24 via `/v1/models` live et docs officielles, free tiers recurrents confirmes sans Pollen.
 
 > 💡 One key is enough to start. Add more at any time by pressing **`P`** inside the TUI (or via the Web Dashboard **Settings** page). A few providers (`Kilo`, `LLM7`, OVHcloud sandbox) can even answer without a key, with tighter shared limits.
 
@@ -231,7 +236,7 @@ To protect you, FCM:
 
 The TUI is the heart of FCM. Launch it with `free-coding-models` and you get a live, sortable table of every model — real latency, stability, verdict, and a one-key launch into your coding tool.
 
-<p align="center"><video src="website/public/videos/tui-first-launch.mp4" alt="First launch — ~222 models ping in parallel" autoplay muted loop playsinline width="100%"></video></p>
+<p align="center"><video src="website/public/videos/tui-first-launch.mp4" alt="First launch — many models ping in parallel" autoplay muted loop playsinline width="100%"></video></p>
 
 ### First-run flow
 
@@ -761,7 +766,7 @@ Every routed request through the daemon feeds a persistent per-model telemetry f
 
 ### Features at a glance
 
-- **Parallel pings** — all ~222 models tested simultaneously via native `fetch`
+- **Parallel pings** — all models tested simultaneously via native `fetch`
 - **AI benchmark columns** — `Ctrl+A` / `Ctrl+U` split into AI Latency + TPS; optional Startup AI Speed Scan
 - **Adaptive monitoring** — 2s burst for 60s → 10s normal → 30s idle
 - **Stability score** — composite 0–100 (p95, jitter, spike rate, uptime)
@@ -801,7 +806,7 @@ A: Yes — see [`sources.js`](./sources.js) for the model catalog format.
 
 ## ⚖️ Model Licensing & Commercial Use
 
-**Short answer:** the ~222 cataloged models are API/CLI-served models where generated-output ownership is generally granted by the provider/model terms. **You own the generated output** — code, text, or otherwise — and can use it commercially. The licenses below govern the *model weights themselves*, not your generated content.
+**Short answer:** the cataloged models are API/CLI-served where generated-output ownership is generally granted by the provider/model terms. **You own the generated output** — code, text, or otherwise — and can use it commercially. The licenses below govern the *model weights themselves*, not your generated content.
 
 | License | Models | Commercial Output |
 |---------|--------|:-----------------:|

package/changelog/v0.5.81.md

@@ -0,0 +1,25 @@
+# Changelog v0.5.81 - 2026-08-24
+
+### Added
+- **3 new free recurring providers** (total 22 providers, ~207 models)
+  - **Pollinations AI** — 10 models `gen.pollinations.ai/v1` : `laguna`, `minimax-m2.7`, `qwen-coder`, `deepseek`, `kimi-code`, `openai`, `gemma-4-31b`, `gpt-oss`, `qwen3.7-flash`, `nemotron-3.5-lightning` — free via daily Pollen grants (Quest 3.25) , ⚠️ experimental integration not yet confirmed stable (Pollen system may change, `MISS` = 402 when balance 0, `HIT` cache may still 200)
+  - **SiliconFlow** — 3 models `api.siliconflow.cn/v1` : `THUDM/GLM-Z1-9B-0414`, `Qwen/Qwen3-8B`, `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B` — 3 models @ $0 forever, 1000 RPM, phone SMS required, verified 2026-08-24 via pricing page
+  - **Requesty** — 12 models `router.requesty.ai/v1` : `nvidia/nemotron-3-ultra-550b-a55b`, `poolside/laguna-xs.2`, `nvidia/nemotron-3-super`, `poolside/laguna-m.1`, `google/gemma-4-31b-it`, `nvidia/nemotron-3-nano-omni`, `nvidia/nemotron-3-nano`, `nvidia/nemotron-3.5-lightning-30b-a3b`, `mistral/leanstral-1-5`, `novita/ling-3.0-tiny`, `nvidia/content-safety`, `nvidia/muse-glimmer-30b` — 200 req/day free no card, 4x OpenRouter, verified live via `GET /v1/models` 676 models 12 zero-price
+- **Provider metadata** for the 3 new providers: `ENV_VAR_NAMES` (`POLLINATIONS_API_KEY`, `SILICONFLOW_API_KEY`, `REQUESTY_API_KEY`), `PROVIDER_METADATA` labels/couleurs/signupHint/rateLimits with detailed Pollen explanation, `PROVIDER_CAPABILITIES` daily reset, `PROVIDER_AUTH_ENDPOINTS` fixes
+- **Theme colors** for `pollinations` (pink) and `requesty` (blue) in both dark/light palettes
+- **Pollen help** in Settings overlay and README/website: explains Pollen ≈ $1, daily Quest grants via tier/quests, 0 Pollen = 402, HIT vs MISS, wallet `enter.pollinations.ai`, grants at midnight UTC, experimental note
+
+### Changed
+- **README** : removed hard-coded total counts everywhere (super chiant a maintenir) — `~207 models across 22 providers` -> `a large catalog of free coding models from 20+ providers`, badges `models-207` -> `models-large catalog` `providers-22` -> `providers-20+`, `~222` video caption -> `many`, `Parallel pings all ~207` -> `all models`, `~207 cataloged` -> `the cataloged`; provider table updated to 22 rows with real per-provider counts and new Pollinations/SiliconFlow/Requesty rows, added Pollen explainer block after table (with experimental warning) and SiliconFlow/Requesty verified note; removed GitHub Models from active table (retired 2026-07-30)
+- **Website docs** : `website/src/content/docs/introduction.mdx` and `quick-start.mdx` and `core/providers.mdx` and `docs/development.md` and `routes/index.tsx` hero `222+` -> `Many` — same generic wording, no hard totals
+- **Pollinations experimental flag** : README and `website/src/content/docs/core/providers.mdx` mark Pollinations `⚠️ experimental` and note `not yet confirmed stable`
+
+### Fixed
+- **SiliconFlow baseURL** : `api.siliconflow.com` -> `api.siliconflow.cn` in `src/core/opencode.js` (2 sites) and `src/core/kilo.js` and `src/core/provider-key-tester.js` `siliconflow` endpoint now `https://api.siliconflow.cn/v1/models`
+- **Provider key tester** : `pollinations` and `requesty` set to `null` (their `/v1/models` are public without auth, so auth-only probe would always 200 and give false ok, now it falls back to ping which correctly shows 402 when balance 0)
+- **Sync** : `sync-website-sources.sh` run -> `website/src/_fcm-sources/sources.js` updated to 22 providers
+
+### Verified
+- `pnpm test` 813 pass 0 fail
+- `node -e import('./sources.js')` 22 providers 207 models 0 dups
+- Live probes 2026-08-24: Pollinations `sk_GCaY...` and `sk_0dSR...` both `402` on MISS with `0.0000` balance (HIT still 200 via fallback), Quest wallet `3.25` not yet linked to keys (Budget ∞ but still 0), Requesty 12 zero-price confirmed, SiliconFlow pricing page verified

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.80",
+  "version": "0.5.81",
   "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",
@@ -76,7 +76,7 @@
     "@tabler/icons-react": "^3.44.0",
     "@tanstack/react-table": "^8.21.3",
     "chalk": "^5.6.2",
-    "kandown": "^0.50.0",
+    "kandown": "^0.52.0",
     "socket.io": "^4.8.3",
     "socket.io-client": "^4.8.3",
     "@tanstack/react-virtual": "^3.14.2"

package/sources.js

@@ -29,7 +29,7 @@
  *   📖 Secondary: https://swe-rebench.com (independent evals, scores are lower)
  *   📖 Leaderboard tracker: https://www.marc0.dev/en/leaderboard
  *
- *   @exports nvidiaNim, groq, cerebras, sambanova, openrouter, githubModels, mistral, codestral, scaleway, googleai, zai, qwen, cloudflare, ovhcloud, opencodeZen, kilo, llm7, routeway, novita, ollamaCloud — model arrays per active provider
+ *   @exports nvidiaNim, groq, cerebras, sambanova, openrouter, githubModels, mistral, codestral, scaleway, googleai, zai, qwen, cloudflare, ovhcloud, opencodeZen, kilo, llm7, routeway, novita, ollamaCloud, pollinations, siliconflow, requesty — model arrays per active provider
  *   @exports sources — map of active free/free-limited providers, each with { name, url, models }
 
  *   @exports MODELS — flat array of [modelId, label, tier, sweScore, ctx, providerKey]
@@ -450,6 +450,68 @@ export const novita = [
   // Removed (2026-07-27): qwen/qwen3.5-plus (Qwen3.5 Plus) — no longer in novita catalog
 ]
 
+// 📖 Pollinations AI source - https://gen.pollinations.ai
+// 📖 OpenAI-compatible endpoint: https://gen.pollinations.ai/v1/chat/completions
+// 📖 Free tier: anonymous without key or free API key from https://enter.pollinations.ai
+// 📖 Daily Pollen grants per tier (seed/flower/nectar) — free models cost Pollen but grants renew daily; anonymous tier has rate limits.
+// 📖 Verified live 2026-08-23 via GET /v1/models (319 models); IDs below are live and coding-relevant.
+export const pollinations = [
+  // ── S+ tier — SWE-bench Verified ≥70% ──
+  ['laguna', 'Laguna XS.2', 'S+', '70.9%', '1M'],
+  ['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '200k'],
+  // ── S tier — SWE-bench Verified 60–70% ──
+  ['qwen-coder', 'Qwen3 Coder', 'S', '69.6%', '262k'],
+  ['deepseek', 'DeepSeek V3', 'S', '66.0%', '1M'],
+  ['kimi-code', 'Kimi K2 Code', 'S', '60.4%', '262k'],
+  ['openai', 'OpenAI GPT', 'S', '62.4%', '400k'],
+  // ── A+ tier — SWE-bench Verified 50–60% ──
+  ['gemma-4-31b', 'Gemma 4 31B', 'A+', '52.0%', '262k'],
+  ['gpt-oss', 'GPT OSS 20B', 'A+', '50.3%', '131k'],
+  ['qwen3.7-flash', 'Qwen3.7 Flash', 'A+', '-', '1M'],
+  // ── B+ tier ──
+  ['nemotron-3.5-lightning', 'Nemotron 3.5 Lightning', 'B+', '-', '262k'],
+]
+
+// 📖 SiliconFlow source - https://api.siliconflow.cn/v1/chat/completions
+// 📖 OpenAI-compatible endpoint: https://api.siliconflow.cn/v1
+// 📖 Free tier: permanently free models at $0 (no card needed beyond phone SMS verification).
+// 📖 Verified 2026-08-23 via pricing page + docs: THUDM/GLM-Z1-9B-0414 is 免费; Qwen3-8B and DeepSeek-R1-Distill-Qwen-7B
+// 📖 documented as free in SiliconFlow guide 2026-06-05 ("Three models are completely free: Qwen3-8B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-OCR")
+// 📖 and still reachable with free-tier rate limits (1000 RPM). Keep only the chat text models here.
+export const siliconflow = [
+  // ── A tier — SWE-bench Verified 40–50% ──
+  ['THUDM/GLM-Z1-9B-0414', 'GLM-Z1 9B', 'A', '-', '32k'],
+  // ── B+ tier ──
+  ['Qwen/Qwen3-8B', 'Qwen3 8B', 'B+', '30.0%', '32k'],
+  ['deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', 'DeepSeek R1 Distill Qwen 7B', 'A', '-', '32k'],
+]
+
+// 📖 Requesty source - https://router.requesty.ai/v1
+// 📖 OpenAI-compatible gateway: https://router.requesty.ai/v1/chat/completions
+// 📖 Free tier: 200 req/day on zero-price free models (4× OpenRouter), no card, EU residency, routing/caching included.
+// 📖 Verified live 2026-08-23 via GET /v1/models (676 models, 12 with input_price=0 & output_price=0).
+export const requesty = [
+  // ── S+ tier — SWE-bench Verified ≥70% ──
+  ['nvidia/nemotron-3-ultra-550b-a55b', 'Nemotron 3 Ultra', 'S+', '71.9%', '1M'],
+  ['poolside/laguna-xs.2', 'Laguna XS.2', 'S+', '70.9%', '32k'],
+  // ── S tier — SWE-bench Verified 60–70% ──
+  ['nvidia/nemotron-3-super-120b-a12b', 'Nemotron 3 Super', 'S', '60.5%', '1M'],
+  ['poolside/laguna-m.1', 'Laguna M.1', 'S', '-', '32k'],
+  // ── A+ tier — SWE-bench Verified 50–60% ──
+  ['google/gemma-4-31b-it', 'Gemma 4 31B', 'A+', '52.0%', '262k'],
+  ['nvidia/nemotron-3-nano-omni-30b-a3b-reasoning', 'Nemotron 3 Omni', 'A+', '52.0%', '131k'],
+  // ── A tier — SWE-bench Verified 40–50% ──
+  ['nvidia/nemotron-3-nano-30b-a3b', 'Nemotron Nano 30B', 'A-', '38.8%', '262k'],
+  // ── B+ tier — SWE-bench Verified 30–35% ──
+  ['nvidia/nemotron-3.5-lightning-30b-a3b', 'Nemotron 3.5 Lightning', 'B+', '-', '1M'],
+  // ── B tier — SWE-bench Verified 20–30% ──
+  ['mistral/leanstral-1-5', 'Leanstral 1.5', 'B', '-', '262k'],
+  ['novita/inclusionai/ling-3.0-tiny', 'Ling 3.0 Tiny', 'B', '-', '262k'],
+  // ── C tier — other zero-price models (kept for breadth) ──
+  ['nvidia/nemotron-3.5-content-safety', 'Nemotron Content Safety', 'C', '-', '131k'],
+  ['nvidia/muse-glimmer-30b', 'Muse Glimmer 30B', 'C', '-', '131k'],
+]
+
 // 📖 Ollama Cloud source - https://ollama.com/pricing and https://ollama.com/search?c=cloud
 // 📖 Free plan includes cloud model access with session/weekly limits. This list keeps coding-relevant cloud models only.
 // 📖 Catalog verified 2026-07-18 against official Ollama cloud model search page.
@@ -629,6 +691,27 @@ export const sources = {
     quotaCode: 'limited',
     models: novita, // Empty — kept for backward compat in user configs
   },
+  pollinations: {
+    name: 'Pollinations AI',
+    url: 'https://gen.pollinations.ai/v1/chat/completions',
+    quota: 'Free · daily Pollen grants · key at enter.pollinations.ai',
+    quotaCode: 'free',
+    models: pollinations,
+  },
+  siliconflow: {
+    name: 'SiliconFlow',
+    url: 'https://api.siliconflow.cn/v1/chat/completions',
+    quota: 'Free · 3 models @ $0 · 1000 RPM',
+    quotaCode: 'free',
+    models: siliconflow,
+  },
+  requesty: {
+    name: 'Requesty',
+    url: 'https://router.requesty.ai/v1/chat/completions',
+    quota: 'Free · 200 req/day · no card',
+    quotaCode: 'free',
+    models: requesty,
+  },
   'ollama-cloud': {
     name: 'Ollama Cloud',
     url: 'https://ollama.com/v1/chat/completions',

package/src/core/config.js

@@ -183,6 +183,9 @@ const ENV_VARS = {
   routeway:   'ROUTEWAY_API_KEY',
   novita:     'NOVITA_API_KEY',
   'ollama-cloud': 'OLLAMA_API_KEY',
+  pollinations: ['POLLINATIONS_API_KEY', 'POLLINATIONS_TOKEN'],
+  siliconflow: 'SILICONFLOW_API_KEY',
+  requesty:   'REQUESTY_API_KEY',
 }
 
 // 📖 Smart Router defaults are intentionally conservative: balanced probing,

package/src/core/kilo.js

@@ -163,7 +163,7 @@ export async function startKilo(model, fcmConfig) {
       config.provider.siliconflow = {
         npm: '@ai-sdk/openai-compatible',
         name: 'SiliconFlow',
-        options: { baseURL: 'https://api.siliconflow.com/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
+        options: { baseURL: 'https://api.siliconflow.cn/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
         models: {}
       }
     } else if (providerKey === 'together') {

package/src/core/opencode.js

@@ -478,7 +478,7 @@ export async function startOpenCode(model, fcmConfig) {
       config.provider.siliconflow = {
         npm: '@ai-sdk/openai-compatible',
         name: 'SiliconFlow',
-        options: { baseURL: 'https://api.siliconflow.com/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
+        options: { baseURL: 'https://api.siliconflow.cn/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
         models: {}
       }
     } else if (providerKey === 'together') {
@@ -846,7 +846,7 @@ export async function startOpenCodeDesktop(model, fcmConfig) {
       config.provider.siliconflow = {
         npm: '@ai-sdk/openai-compatible',
         name: 'SiliconFlow',
-        options: { baseURL: 'https://api.siliconflow.com/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
+        options: { baseURL: 'https://api.siliconflow.cn/v1', apiKey: '{env:SILICONFLOW_API_KEY}' },
         models: {}
       }
     } else if (providerKey === 'together') {

package/src/core/provider-key-tester.js

@@ -65,7 +65,9 @@ export const PROVIDER_AUTH_ENDPOINTS = {
   fireworks:    { url: 'https://api.fireworks.ai/v1/models',         method: 'GET' },
   hyperbolic:   { url: 'https://api.hyperbolic.xyz/v1/models',       method: 'GET' },
   scaleway:     { url: 'https://api.scaleway.ai/v1/models',          method: 'GET' },
-  siliconflow:  { url: 'https://api.siliconflow.com/v1/models',     method: 'GET' },
+  siliconflow:  { url: 'https://api.siliconflow.cn/v1/models',     method: 'GET' },
+  pollinations: null,
+  requesty:     null,
   together:     { url: 'https://api.together.xyz/v1/models',        method: 'GET' },
   perplexity:   { url: 'https://api.perplexity.ai/v1/models',       method: 'GET' },
   chutes:       { url: 'https://chutes.ai/v1/models',               method: 'GET' },

package/src/core/provider-metadata.js

@@ -62,6 +62,9 @@ export const ENV_VAR_NAMES = {
   routeway:   'ROUTEWAY_API_KEY',
   novita:     'NOVITA_API_KEY',
   'ollama-cloud': 'OLLAMA_API_KEY',
+  pollinations: 'POLLINATIONS_API_KEY',
+  siliconflow: 'SILICONFLOW_API_KEY',
+  requesty:   'REQUESTY_API_KEY',
 }
 
 // 📖 OPENCODE_MODEL_MAP: sparse table of model IDs that differ between sources.js and OpenCode's
@@ -201,13 +204,6 @@ export const PROVIDER_METADATA = {
     signupHint: 'Get API key',
     rateLimits: 'Gemini free quotas vary by model and region',
   },
-  siliconflow: {
-    label: 'SiliconFlow',
-    color: chalk.rgb(178, 235, 242),
-    signupUrl: 'https://cloud.siliconflow.cn/account/ak',
-    signupHint: 'API Keys → Create',
-    rateLimits: 'Free models: usually 100 RPM, varies by model',
-  },
   together: {
     label: 'Together AI',
     color: chalk.rgb(255, 241, 118),
@@ -312,6 +308,28 @@ export const PROVIDER_METADATA = {
     rateLimits: 'Only zero-price live chat models are listed; other Novita models are paid/trial-credit',
     paidProviderNote: 'paid — 3 free models',
   },
+  pollinations: {
+    label: 'Pollinations AI ⚠️ experimental',
+    color: chalk.rgb(255, 105, 180),
+    signupUrl: 'https://enter.pollinations.ai',
+    signupHint: 'enter.pollinations.ai → API Keys (free Pollen daily; star github.com/pollinations/pollinations to earn Pollen; 0 Pollen = 402; no purchase needed)',
+    rateLimits: 'Free via Pollen (daily grants; ~0.0001-0.003 Pollen/req; 0 Pollen = 402; experimental, system may change)',
+    detailedLimits: 'Pollen ≈ $1. Daily free Pollen via tier (seed/flower/nectar) + quests (star repo, help issue). No purchase required. Cost per request 0.0001-0.003 Pollen. If balance is 0.0000, every MISS returns 402 PAYMENT_REQUIRED and the TUI shows 402; HIT (Cloudflare cache) may still return 200 but is not reliable. Check balance at enter.pollinations.ai → API Keys. Grants reset daily at midnight UTC. Integration is experimental and not yet confirmed as stable.',
+  },
+  siliconflow: {
+    label: 'SiliconFlow',
+    color: chalk.rgb(178, 235, 242),
+    signupUrl: 'https://cloud.siliconflow.cn/account/ak',
+    signupHint: 'API Keys → Create (phone SMS verification required)',
+    rateLimits: 'Free · 3 models @ $0 · 1000 RPM · 1M tokens/day per model',
+  },
+  requesty: {
+    label: 'Requesty',
+    color: chalk.rgb(100, 149, 255),
+    signupUrl: 'https://app.requesty.ai/api-keys',
+    signupHint: 'API Keys → Create (200 req/day free, no card)',
+    rateLimits: 'Free · 200 req/day on free models (20 req/min) · no card',
+  },
   'ollama-cloud': {
     label: 'Ollama Cloud',
     color: chalk.rgb(230, 230, 230),

package/src/core/quota-capabilities.js

@@ -61,6 +61,9 @@ export const PROVIDER_CAPABILITIES = {
   routeway: { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'unknown' },
   novita: { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'unknown' },
   'ollama-cloud': { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'rolling' },
+  pollinations: { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'daily' },
+  siliconflow: { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'daily' },
+  requesty: { telemetryType: 'unknown', supportsEndpoint: false, usageDisplay: 'ok', resetCadence: 'daily' },
 }
 
 /** Fallback for unrecognized providers */

package/src/tui/theme.js

@@ -192,6 +192,8 @@ const PROVIDER_PALETTES = {
     llm7: [180, 255, 140],
     routeway: [130, 210, 255],
     novita: [255, 185, 120],
+    pollinations: [255, 105, 180],
+    requesty: [100, 149, 255],
     'ollama-cloud': [230, 230, 230],
   },
   light: {
@@ -222,6 +224,8 @@ const PROVIDER_PALETTES = {
     llm7: [73, 130, 0],
     routeway: [0, 105, 180],
     novita: [173, 84, 0],
+    pollinations: [170, 45, 110],
+    requesty: [0, 72, 170],
     'ollama-cloud': [88, 88, 88],
   },
 }