# LLM Perks

> A live catalog of language models with free API access — providers, limits, context windows, benchmarks — plus free AI software, AI credits, referral programs, subscription ROI, and infrastructure.

Snapshot: 2026-11-02T17:25:28.049Z
Free models: 269 (360 endpoints) · Providers online: 16/16
Free software: 73 · AI credit programs: 74 · Referral programs: 33 · Subscriptions: 53
Benchmarks: Artificial Analysis (2026-09-24), https://artificialanalysis.ai/

## Sections

- [Free model catalog](https://llmperks.com)
- [Model families](https://llmperks.com/models)
- [Provider comparison](https://llmperks.com/providers)
- [New free models](https://llmperks.com/new): endpoints added in 30 days and removed in 14 days
- [Free AI software](https://llmperks.com/software)
- [Free AI credits](https://llmperks.com/credits)
- [AI referral programs](https://llmperks.com/referrals)
- [AI subscription ROI](https://llmperks.com/subscriptions)
- [Subscription ROI methodology](https://llmperks.com/subscriptions/methodology)
- [Infrastructure](https://llmperks.com/infrastructure)
- [Blog](https://llmperks.com/blog)
- [Full data dump](https://llmperks.com/llms-full.txt)
- [Telegram](https://t.me/freellms_bot)

## Best free models right now

- [GLM 5.3 Flash](https://llmperks.com/glm/glm-5-3-flash): AA index 41.8, 1000000 ctx, free at orcarouter, nvidia, unorouter, opencode
- [GLM 5.3](https://llmperks.com/glm/glm-5-3): AA index 44.8, 1048576 ctx, free at together
- [DeepSeek V4.1 Flash](https://llmperks.com/deepseek/deepseek-v4-1-flash): AA index 39.5, 1000000 ctx, free at orcarouter, nvidia, unorouter, opencode
- [Step 5 Preview](https://llmperks.com/step/step-5-preview): AA index 43.7, 1000000 ctx, free at nvidia
- [GLM 5.3 Flash Thinking](https://llmperks.com/glm/glm-5-3-flash-thinking): AA index 41.8, 1000000 ctx, free at unorouter
- [Gemini 3.8 Flash](https://llmperks.com/gemini/gemini-3-8-flash): AA index 40.9, 1048576 ctx, free at gemini
- [Qwen 3.8 27B](https://llmperks.com/qwen/qwen3-8-27b): AA index 33.7, 262144 ctx, free at groq, cloudflare, unorouter
- [DeepSeek V4 Flash](https://llmperks.com/deepseek/deepseek-v4-flash): AA index 34.3, 1000000 ctx, free at orcarouter
- [Gemini 3.6 Flash](https://llmperks.com/gemini/gemini-3-6-flash): AA index 34.0, 1000000 ctx, free at unorouter
- [GLM 5.2](https://llmperks.com/glm/glm-5-2): AA index 33.7, 1048576 ctx, free at together
- [Inkling Small](https://llmperks.com/inkling/inkling-small): AA index 27.8, 1048576 ctx, free at openrouter
- [Kimi K2.6](https://llmperks.com/kimi/kimi-k2-6): AA index 27.0, 256000 ctx, free at nvidia
- [Nemotron 3 Ultra](https://llmperks.com/nemotron/nemotron-3-ultra): AA index 22.9, 1048576 ctx, free at openrouter, nvidia, unorouter
- [Inkling](https://llmperks.com/inkling/inkling): AA index 25.0, 1048576 ctx, free at openrouter
- [Hy3](https://llmperks.com/hunyuan/hy3): AA index 25.3, 256000 ctx, free at orcarouter
- [Gemma 4 31B](https://llmperks.com/gemma/gemma-4-31b): AA index 19.0, 262144 ctx, free at openrouter, together, nvidia, unorouter
- [Gemini 3.5 Flash Lite](https://llmperks.com/gemini/gemini-3-5-flash-lite): AA index 22.2, 1000000 ctx, free at unorouter
- [MiniMax M2.5](https://llmperks.com/minimax/minimax-m2-5): AA index 22.8, 204800 ctx, free at unorouter
- [Qwen 3.5 397B](https://llmperks.com/qwen/qwen3-5-397b): AA index 21.4, 262100 ctx, free at unorouter
- [Qwen 3.6 27B](https://llmperks.com/qwen/qwen3-6-27b): AA index 21.4, 262100 ctx, free at unorouter
- [Gemma 4 26B A4B](https://llmperks.com/gemma/gemma-4-26b): AA index 16.7, 262144 ctx, free at openrouter, together, cloudflare, unorouter
- [GLM 4.7](https://llmperks.com/glm/glm-4-7): AA index 22.2, 202752 ctx, free at together
- [Qwen 3.6 35B](https://llmperks.com/qwen/qwen3-6-35b): AA index 18.2, 262144 ctx, free at together, unorouter
- [Step 3.7 Flash](https://llmperks.com/step/step-3-7-flash): AA index 19.5, 262144 ctx, free at nous
- [Qwen 3.5 35B](https://llmperks.com/qwen/qwen3-5-35b): AA index 19.3, 262144 ctx, free at together

## Collections and use cases

- [Free models for AI agents](https://llmperks.com/for/ai-agents)
- [Free models for coding](https://llmperks.com/for/coding)
- [Free reasoning models](https://llmperks.com/for/reasoning)
- [Free long-context models](https://llmperks.com/for/long-context)
- [Free vision models](https://llmperks.com/for/vision)
- [Free image generation models](https://llmperks.com/for/image)
- [Free video generation models](https://llmperks.com/for/video)
- [Free music and audio models](https://llmperks.com/for/music)
- [Free frontier model APIs](https://llmperks.com/for/frontier)
- [Free open-weight model APIs](https://llmperks.com/for/open-weights)

## Providers

- [OpenRouter](https://llmperks.com/openrouter): Models with the :free suffix allow 50 requests per day, or 1,000 per day after a one-time $10 top-up (20 requests per minute). Base URL: https://openrouter.ai/api/v1
- [Groq](https://llmperks.com/groq): Free plan with per-model limits on requests and tokens per minute and per day; very high generation speed on LPU hardware. Base URL: https://api.groq.com/openai/v1
- [Google AI Studio](https://llmperks.com/gemini): The Gemini API free tier covers Flash and Flash-Lite models with rate limits; free-tier content may be used to improve Google products. Base URL: https://generativelanguage.googleapis.com/v1beta/openai/
- [Mistral AI](https://llmperks.com/mistral): The Free plan includes monthly API credits for Mistral models, with low default rate limits. Base URL: https://api.mistral.ai/v1
- [Together AI](https://llmperks.com/together): Only selected models are priced at zero; there is no general free trial. Base URL: https://api.together.xyz/v1
- [Cohere](https://llmperks.com/cohere): Trial keys allow 1,000 API calls per month for evaluation, not for production. Base URL: https://api.cohere.ai/compatibility/v1
- [Cerebras](https://llmperks.com/cerebras): Free trial with daily token limits; a verified payment method is required to activate the API. Base URL: https://api.cerebras.ai/v1
- [Cloudflare Workers AI](https://llmperks.com/cloudflare): 10,000 Neurons per day are free on both Workers Free and Paid plans. Base URL: https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1
- [Hugging Face](https://llmperks.com/huggingface): Free accounts get a small monthly credit for Inference Providers; PRO accounts get more. Base URL: https://router.huggingface.co/v1
- [OrcaRouter](https://llmperks.com/orcarouter): BYOK router without token markup; its own Fusion models and selected free routes cost nothing. Base URL: https://api.orcarouter.ai/v1
- [NVIDIA Build](https://llmperks.com/nvidia): Free serverless inference for development and prototyping with a developer account; not intended for production traffic. Base URL: https://integrate.api.nvidia.com/v1
- [TokenRouter](https://llmperks.com/tokenrouter): Free models and promotional access may be time-limited. Base URL: https://api.tokenrouter.com/v1
- [Vercel AI Gateway](https://llmperks.com/vercel): A payment card must be on file even for zero-price models. Base URL: https://ai-gateway.vercel.sh/v1
- [Nous Portal](https://llmperks.com/nous): The $0 Portal plan includes :free models with standard rate limits. Base URL: https://inference-api.nousresearch.com/v1
- [UnoRouter](https://llmperks.com/unorouter): Large catalog of :free routes without a card; shared capacity and per-model limits. Base URL: https://api.unorouter.com/v1
- [OpenCode Zen](https://llmperks.com/opencode): Models with the -free suffix cost nothing for a limited time; prompts may be used to improve the model. Base URL: https://opencode.ai/zen/v1

## Free software by category

- [AI agents](https://llmperks.com/software/agents): 10
- [Terminal coding agents](https://llmperks.com/software/cli-agents): 8
- [AI code editors](https://llmperks.com/software/ide): 11
- [IDE extensions](https://llmperks.com/software/ide-extensions): 4
- [Local LLM runners](https://llmperks.com/software/local-llm): 11
- [Chat interfaces](https://llmperks.com/software/chat-ui): 8
- [Automation and no-code](https://llmperks.com/software/automation): 6
- [Image and video](https://llmperks.com/software/image-video): 7
- [Voice and speech](https://llmperks.com/software/voice): 8

## AI credits

- [All AI credits](https://llmperks.com/credits): The full verified list
- [Free API credits](https://llmperks.com/credits/signup): Free tiers and signup credits
- [AI grants for startups](https://llmperks.com/credits/startup): Up to $350,000 for cloud and models
- [AI credits for students](https://llmperks.com/credits/student): Plans and credits for students
- [No card required](https://llmperks.com/credits/no-card): Credits and plans without a card
- [Referral programs](https://llmperks.com/referrals): Credits and usage for invites

## Subscriptions by provider

- [Anthropic](https://llmperks.com/subscriptions/anthropic): Claude Pro $20 → API value $55 (https://llmperks.com/subscriptions/anthropic/claude-pro); Claude Max 5x $100 → API value $280 (https://llmperks.com/subscriptions/anthropic/claude-max-5x); Claude Max 20x $200 → API value $1200 (https://llmperks.com/subscriptions/anthropic/claude-max-20x)
- [OpenAI](https://llmperks.com/subscriptions/openai): ChatGPT Go $8 → API value $8 (https://llmperks.com/subscriptions/openai/chatgpt-go); ChatGPT Plus $20 → API value $280 (https://llmperks.com/subscriptions/openai/chatgpt-plus); ChatGPT Business $25 → API value $160 (https://llmperks.com/subscriptions/openai/chatgpt-business); ChatGPT Enterprise $50 → API value $400 (https://llmperks.com/subscriptions/openai/chatgpt-enterprise); ChatGPT Pro 100 $100 → API value $1056 (https://llmperks.com/subscriptions/openai/chatgpt-pro-100); ChatGPT Pro 200 $200 → API value $1625 (https://llmperks.com/subscriptions/openai/chatgpt-pro-200); ChatGPT Pro 500 $500 → API value $2195 (https://llmperks.com/subscriptions/openai/chatgpt-pro-500)
- [Google](https://llmperks.com/subscriptions/google): AI Plus $4.99 → API value $18 (https://llmperks.com/subscriptions/google/google-ai-plus); AI Pro $19.99 → API value $150 (https://llmperks.com/subscriptions/google/google-ai-pro); AI Ultra 5x $99.99 → API value $400 (https://llmperks.com/subscriptions/google/google-ai-ultra-5x); AI Ultra 20x $199.99 → API value $800 (https://llmperks.com/subscriptions/google/google-ai-ultra-20x)
- [xAI](https://llmperks.com/subscriptions/xai): X Premium $8 → API value $16 (https://llmperks.com/subscriptions/xai/x-premium); SuperGrok Lite $10 → API value $22 (https://llmperks.com/subscriptions/xai/supergrok-lite); SuperGrok $30 → API value $95 (https://llmperks.com/subscriptions/xai/supergrok); SuperGrok Plus $100 → API value $320 (https://llmperks.com/subscriptions/xai/supergrok-plus); SuperGrok Heavy $300 → API value $950 (https://llmperks.com/subscriptions/xai/supergrok-heavy)
- [GitHub Copilot](https://llmperks.com/subscriptions/github-copilot): Pro $10 → API value $40 (https://llmperks.com/subscriptions/github-copilot/copilot-pro); Pro+ $39 → API value $90 (https://llmperks.com/subscriptions/github-copilot/copilot-pro-plus)
- [Cursor](https://llmperks.com/subscriptions/cursor): Pro $20 → API value $20 (https://llmperks.com/subscriptions/cursor/cursor-pro); Pro+ $60 → API value $70 (https://llmperks.com/subscriptions/cursor/cursor-pro-plus); Ultra $200 → API value $400 (https://llmperks.com/subscriptions/cursor/cursor-ultra)
- [Windsurf](https://llmperks.com/subscriptions/windsurf): Pro $20 → API value $85 (https://llmperks.com/subscriptions/windsurf/windsurf-pro); Max $200 → API value $420 (https://llmperks.com/subscriptions/windsurf/windsurf-max)
- [Poe](https://llmperks.com/subscriptions/poe): Standard $19.99 → API value $45 (https://llmperks.com/subscriptions/poe/poe-standard)
- [Trae.ai](https://llmperks.com/subscriptions/trae): Lite $3 → API value $25 (https://llmperks.com/subscriptions/trae/trae-lite); Pro $10 → API value $85 (https://llmperks.com/subscriptions/trae/trae-pro); Ultra $100 → API value $920 (https://llmperks.com/subscriptions/trae/trae-ultra)
- [Command Code](https://llmperks.com/subscriptions/command-code): Go $1 → API value $10 (https://llmperks.com/subscriptions/command-code/command-code-go); GOAT $10 → API value $70 (https://llmperks.com/subscriptions/command-code/command-code-goat); Pro $20 → API value $80 (https://llmperks.com/subscriptions/command-code/command-code-pro); Max 10x $100 → API value $150 (https://llmperks.com/subscriptions/command-code/command-code-max-10x); Max 20x $200 → API value $300 (https://llmperks.com/subscriptions/command-code/command-code-max-20x)
- [Z.ai](https://llmperks.com/subscriptions/zai): GLM Coding Lite $18 → API value $270 (https://llmperks.com/subscriptions/zai/zai-coding-lite); GLM Coding Pro $72 → API value $1080 (https://llmperks.com/subscriptions/zai/zai-coding-pro); GLM Coding Max $160 → API value $2400 (https://llmperks.com/subscriptions/zai/zai-coding-max)
- [Kimi](https://llmperks.com/subscriptions/kimi): Andante $6.8 → API value $6.8 (https://llmperks.com/subscriptions/kimi/kimi-andante); Moderato $13.8 → API value $13.8 (https://llmperks.com/subscriptions/kimi/kimi-moderato); Allegretto $27.6 → API value $27.6 (https://llmperks.com/subscriptions/kimi/kimi-allegretto); Allegro $97.1 → API value $97.1 (https://llmperks.com/subscriptions/kimi/kimi-allegro)
- [Alibaba Cloud](https://llmperks.com/subscriptions/alibaba): Qwen Pro $50 → API value $580 (https://llmperks.com/subscriptions/alibaba/qwen-pro)
- [BytePlus](https://llmperks.com/subscriptions/byteplus): Coding Lite $10 → API value $10 (https://llmperks.com/subscriptions/byteplus/byteplus-coding-lite); Coding Pro $50 → API value $50 (https://llmperks.com/subscriptions/byteplus/byteplus-coding-pro)
- [Kilo](https://llmperks.com/subscriptions/kilo): Pass Starter $19 → API value $26.6 (https://llmperks.com/subscriptions/kilo/kilo-pass-starter); Pass Pro $49 → API value $68.6 (https://llmperks.com/subscriptions/kilo/kilo-pass-pro); Pass Expert $199 → API value $278.6 (https://llmperks.com/subscriptions/kilo/kilo-pass-expert)
- [MiniMax](https://llmperks.com/subscriptions/minimax): Token Plan Plus $22 → API value $22 (https://llmperks.com/subscriptions/minimax/minimax-token-plus); Token Plan Max $55 → API value $55 (https://llmperks.com/subscriptions/minimax/minimax-token-max); Token Plan Ultra $132 → API value $132 (https://llmperks.com/subscriptions/minimax/minimax-token-ultra)
- [OpenCode](https://llmperks.com/subscriptions/opencode): Go $10 → API value $60 (https://llmperks.com/subscriptions/opencode/opencode-go); Go Plus $40 → API value $240 (https://llmperks.com/subscriptions/opencode/opencode-go-plus)

## Infrastructure

- [Free tiers](https://llmperks.com/infrastructure/free): 14
- [PaaS platforms](https://llmperks.com/infrastructure/paas): 6
- [Virtual servers (VPS)](https://llmperks.com/infrastructure/vps): 3
- [Databases](https://llmperks.com/infrastructure/database): 6
- [Static sites](https://llmperks.com/infrastructure/static): 5
- [For AI agents](https://llmperks.com/infrastructure/agents): 2

## Articles

- [Free OpenCode models as a website pipeline: 8 models compared on real projects](https://llmperks.com/blog/opencode-free-models-site-pipeline): Eight free OpenCode models built 8 working Astro sites and shipped them to Vercel: step timings, failures, article quality, data policies, and which model to assign to which step.
- [Free LLM APIs in 2026: the complete guide](https://llmperks.com/blog/free-llm-api-guide-2026): Where to get free API access to DeepSeek, Qwen, GLM, Kimi, Gemini, and other LLMs in 2026: 15 providers, their limits, card requirements, and how to pick a model without hitting quotas.
- [How to use free LLMs in Cursor, Cline, OpenCode, and VS Code](https://llmperks.com/blog/free-models-in-cursor-cline-opencode): Step-by-step setup of free LLMs in Cline, Kilo Code, OpenCode, Continue, Aider, Zed, and Cursor: base URLs, keys, picking a coding model, and working around limits.
- [Best free coding models: September 2026 ranking](https://llmperks.com/blog/best-free-coding-models-2026): Which free-API models write the best code in September 2026: GLM 5.3, Kimi K3, Qwen 3.8, DeepSeek V4, and more — benchmarks, context, and providers.
- [OpenRouter free tier: :free model limits explained](https://llmperks.com/blog/openrouter-free-limits): How many requests OpenRouter's free models allow in 2026, what the $10 top-up changes, how :free routes work, and when to use the openrouter/free router.
- [Hermes Agent on free models: an autonomous agent for $0](https://llmperks.com/blog/hermes-agent-free-models): How to run Nous Research's Hermes Agent with free OpenRouter or NVIDIA Build models or a local Ollama: setup, model choice, limits, and pitfalls.
- [How to run an LLM locally: Ollama, LM Studio, Jan, and llama.cpp](https://llmperks.com/blog/run-llm-locally-ollama-lm-studio): Comparing free apps for local LLMs in 2026 — Ollama, LM Studio, Jan, llama.cpp — which models fit your hardware and how to connect them to your IDE.
- [Free AI credits in 2026: for developers, startups, and students](https://llmperks.com/blog/free-ai-credits-2026): How to get free AI API and cloud credits in 2026: Gemini API, OpenRouter, AWS Activate, Google for Startups, Microsoft for Startups, and student programs.
- [NVIDIA Nemotron 3 on OpenRouter: free API guide](https://llmperks.com/blog/nvidia-nemotron-3-openrouter): A practical guide to NVIDIA Nemotron 3 Nano, Super, Omni, and Ultra: architecture, context windows, free OpenRouter endpoints, privacy caveats, and API examples.

## Languages

- English: https://llmperks.com
- Deutsch: https://llmperks.com/de
- Français: https://llmperks.com/fr
- Español: https://llmperks.com/es
- Русский: https://free-llms.ru