diff --git a/README.md b/README.md index 91c8dde..1494b51 100644 --- a/README.md +++ b/README.md @@ -8,6 +8,16 @@ Contributions welcome β€” open a pull request or [issue](https://github.com/tiennm99/penny-pincher-provider/issues/new) to add or update an entry. +## Claude AI Ecosystem + +### [ClaudeKit](https://claudekit.cc/) + +ClaudeKit provides tools and resources to work with Claude AI more effectively β€” including prompt templates, workflows, and extensions. + +> Referral: **20% off** your first purchase via (code: `BWA910UK`). + +*Checked Jun 5, 2026.* + --- ## Claude Code Guest Passes @@ -45,7 +55,7 @@ My referral: > > Referral link: -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Z.ai](https://z.ai/subscribe) @@ -54,7 +64,7 @@ Models: GLM-5.1, GLM-5-Turbo. > Referral: -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [MiniMax](https://platform.minimax.io) @@ -68,7 +78,7 @@ Models: M3 (frontier multimodal coding, 1M context), M2.7 (language), M2.7-highs > Referral (10% off) until **Jul 1, 2026** β€” **For Referred Users:** 10% off subscription + become a dev ambassador. **For Referrers:** 10% back in API voucher per paid referral, usable across all MiniMax models, plus priority access to events and model previews. [View details](https://platform.minimax.io/subscribe/token-plan?code=CAQ5sxHAq6&source=link) -*Checked Jun 4, 2026.* +*Checked Jun 5, 2026.* ### [Kimi Code](https://www.kimi.com/code) @@ -76,7 +86,7 @@ Moonshot's coding perk bundled with Kimi membership. Models: Kimi K-series. Roll Tiers: Adagio (free), Andante, Presto. Pay-as-you-go also at `platform.moonshot.ai`. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [BigModel.cn β€” GLM Coding Plan](https://www.bigmodel.cn/glm-coding) @@ -102,7 +112,7 @@ My referral: >πŸš€ Join the GLM Coding Plan via my link β€” get 5% off your first order. Subscribe at https://www.bigmodel.cn/glm-coding?ic=VGRZKHKNKW (invitation code: `VGRZKHKNKW`). -[^bigmodel]: Checked on May 14, 2026 +[^bigmodel]: Checked on Jun 5, 2026 ### [Alibaba Cloud Model Studio β€” Coding Plan](https://www.alibabacloud.com/help/en/model-studio/coding-plan) @@ -111,7 +121,9 @@ Pro plan: **$50/month** β€” 6,000 req/5-hour, 45,000 req/week, 90,000 req/month. Models: qwen3.5-plus, qwen3-max, qwen3-coder, kimi-k2.5, glm-5, MiniMax-M2.5. Tools: Claude Code, Cursor, Cline, Codex, and more. Lite plan no longer accepting new subscribers. -*Checked Apr 30, 2026.* +> Referral: Up to **$1,700** in free trial credits via (code: `A92LU5`). + +*Checked Jun 5, 2026.* ### [BytePlus ModelArk β€” Coding Plan](https://www.byteplus.com/en/activity/codingplan) @@ -120,7 +132,9 @@ ByteDance. Lite: **$5/month**, Pro: **$25/month**. Models: ByteDance-Seed-2.0, DeepSeek-V3.2, GLM-5.1, Kimi-K2.5. Tools: Claude Code, Cursor, Cline, Roo Code, OpenCode. -*Checked Apr 30, 2026.* +> Referral: + +*Checked Jun 5, 2026.* ### [Synthetic](https://synthetic.new/) @@ -129,7 +143,9 @@ Privacy-first inference (no training on prompts/responses). **$30/month** subscr Models: Kimi K2.5, MiniMax M2.5, GLM 5.1, GLM 4.7 Flash, vLLM-compatible open-source models. OpenAI-compatible β€” works with Roo, Cline, Octofriend. -*Checked Apr 22, 2026.* +> Referral: **$10.00** in subscription credit via + +*Checked Jun 5, 2026.* ### [Xiaomi MiMo Open Platform](https://platform.xiaomimimo.com) @@ -139,7 +155,7 @@ After signup, enter the code at the bottom-left of the console. Credits valid 40 > Referral: Code `T8ESAY` Β· -*Checked Jun 4, 2026.* +*Checked Jun 5, 2026.* --- @@ -174,7 +190,7 @@ Meituan. Public beta, no paid tier yet. Resets daily 00:00 Beijing Time. OpenAI + Anthropic compatible endpoints. 256K context on most models. -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [Mistral La Plateforme](https://console.mistral.ai) @@ -182,7 +198,7 @@ Free Experiment plan β€” up to ~1B tokens/month, no credit card (phone verificat Models: Mistral Large 3, Medium 3, Small 3.1, Codestral, Pixtral, embeddings. OpenAI-compatible. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Cerebras Cloud](https://cloud.cerebras.ai) @@ -197,7 +213,7 @@ Wafer-scale chip inference. Free tier, no credit card. 1M tokens/day shared cap. -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [xAI Grok API](https://x.ai/api) @@ -207,13 +223,13 @@ Models: Grok 4, Grok 4.1 Fast (2M ctx), Grok Code Fast. OpenAI + Anthropic compa **Warning:** Data Sharing opt-in is irreversible and lets xAI train on your prompts. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [OpenRouter](https://openrouter.ai) Free models (`:free` suffix): 20 RPM, 50 req/day (free accounts); 1,000 req/day after $10 top-up. -*Checked Mar 25, 2026.* +*Checked Jun 5, 2026.* ### [Groq](https://console.groq.com) @@ -225,7 +241,7 @@ LPU inference. Free tier, no credit card. | `llama-3.3-70b-versatile` | 30 | 1,000 | 12K | 100K | | `whisper-large-v3` | 20 | 2,000 | β€” | β€” | -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [GitHub Models](https://github.com/marketplace/models) @@ -234,7 +250,7 @@ Free for all GitHub accounts. OpenAI-compatible at `https://models.github.ai/inf Covers OpenAI, Anthropic, Llama, Mistral, DeepSeek, Grok, Phi. Rate limits vary per model (e.g. GPT-4o: 10 RPM/50 RPD; DeepSeek-R1: 15 RPM/150 RPD). Requires PAT with `models:read`. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [NVIDIA NIM](https://build.nvidia.com) @@ -242,7 +258,7 @@ Free for NVIDIA Developer Program members, no credit card. ~40 RPM, ~1,000 req/m Models: Kimi K2.5, GPT-OSS, DeepSeek-V3.2, Llama 3.x, Mistral, Phi, Nemotron. OpenAI-compatible. -*Checked Apr 25, 2026.* +*Checked Jun 5, 2026.* ### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) @@ -250,7 +266,7 @@ Models: Kimi K2.5, GPT-OSS, DeepSeek-V3.2, Llama 3.x, Mistral, Phi, Nemotron. Op Models: Llama 3.3 70B, Gemma 3, Qwen2.5-Coder, DeepSeek R1, BGE embeddings, Whisper. -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers) @@ -258,7 +274,7 @@ Routes across Together, Fireworks, Novita, Cerebras, Replicate, DeepInfra, Scale Free: 100K monthly credits. PRO ($9/month): 2M credits. OpenAI-compatible at `https://router.huggingface.co/v1`. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Google Cloud Vertex AI](https://cloud.google.com/vertex-ai) @@ -267,7 +283,7 @@ $300 free credits for 90 days (new GCP customers). Not a recurring free tier. Models: Gemini 3 Pro/Flash, Anthropic Claude on Vertex, DeepSeek, GLM, Qwen via MaaS. Express Mode available without billing for limited evaluation quotas. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [DeepSeek Platform](https://platform.deepseek.com) @@ -275,7 +291,15 @@ Express Mode available without billing for limited evaluation quotas. PAYG: V4 Flash $0.14/M in, $0.28/M out; V4 Pro $0.435/M in, $0.87/M out (cached: $0.03/M). -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* + +### [BigModel.cn](https://www.bigmodel.cn/) + +Zhipu AI (ζ™Ίθ°± AI). 20M free tokens for new users to explore the API, playground, and AGI apps. + +> Referral: + +*Checked Jun 5, 2026.* ### [Scaleway Generative APIs](https://www.scaleway.com/en/generative-apis/) @@ -283,7 +307,7 @@ EU/GDPR, Paris. 1M free tokens for new customers (no time limit advertised). Models: Qwen3 (235B/397B/coder), Llama 3.3 70B, Mistral Small 3.2, DeepSeek R1 distill, Pixtral. -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [Kilo Code β€” Gateway](https://kilo.ai/gateway) @@ -292,7 +316,7 @@ VS Code + JetBrains coding extension with built-in gateway. Free: `:free` models, 200 req/hour per IP. First top-up: $20 bonus credits (60-day expiry). BYOK supported β€” no Kilo subscription required for your own provider keys. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Pollinations AI](https://pollinations.ai) @@ -300,32 +324,32 @@ Open-source, Berlin. Text, image, audio, video. Free publishable key (1 pollen/I Models: DeepSeek V4, Flux, GPT Image, Seedream, Whisper, ElevenLabs voices. OpenAI-compatible. -*Checked Apr 28, 2026.* +*Checked Jun 5, 2026.* ### [Together AI](https://www.together.ai) $25 signup credits (one-time). 200+ models. OpenAI-compatible β€” swap base URL. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [DeepInfra](https://deepinfra.com) Sign-up credits (one-time). 100+ models from $0.02/M. OpenAI-compatible. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Fireworks AI](https://fireworks.ai) $1 starter credits. 50+ models. Function calling, MCP support. OpenAI-compatible. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ### [Modal Labs](https://modal.com) β€” Self-Host $30/month recurring free credits (Starter plan). Deploy any open-source LLM via vLLM as your own OpenAI-compatible endpoint. 3 seats, 100 containers, 10 concurrent GPUs. -*Checked Apr 30, 2026.* +*Checked Jun 5, 2026.* ---