Free AI Models
Every genuinely-free AI model & API (open-weight, free tiers, and no-signup tools), ranked by the community. Each row shows how to use it, how it performs, the free limits, and the catch. No paywalls, no shared keys, no trial-credit traps.
| # | Model | Modality | Access | Performance | Free limits | The catch | ▲ Votes | How to use |
|---|---|---|---|---|---|---|---|---|
| 1 |  Ollama Cloud · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 2 |  Z.ai · ✓ Jul 2026 | TEXTCODE | Open-weight | Strong~ Medium | Self-host free | ✓ no card · ✓ commercial | ||
| 3 |  Google Gemini · ✓ Jul 2026 | IMAGEVIDEOAUDIOTEXT | Free API | unrated | 15 RPM, 1,500 RPD | ✓ no card · ? comm | ||
| 4 |  DeepSeek · ✓ Jul 2026 | TEXTCODE | Open-weight | Frontier~ Medium | Self-host free | ✓ no card · ✓ commercial | ||
| 5 |  Google AI Studio · ✓ Jun 2026 | TEXTIMAGEAUDIO | Free API | Frontier⚡ Fast | Generous · no card | ✓ no card · ✓ commercial | ||
| 6 |  Qwen · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 7 | Google Gemini · ✓ Jul 2026 | IMAGEVIDEOAUDIOTEXT | Free API | unrated | 5 RPM, 50 RPD | ✓ no card · ? comm | ||
| 8 | Google AI Studio · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 9 |  Mistral · ✓ Jul 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 10 |  Hugging Face · ✓ Jun 2026 | TEXTIMAGE | Free API | Solid~ Medium | Rate-limited · 1000s of models | ✓ no card · ✓ commercial | ||
| 11 |  GitHub Models · ✓ Jun 2026 | IMAGETEXT | Free API | unrated | 10 RPM, 50 RPD | ✓ no card · ? comm | ||
| 12 |  Cloudflare Workers AI · ✓ Jul 2026 | TEXT | Free API | unrated | 10K neurons/day (shared) | ✓ no card · ? comm | ||
| 13 |  OpenRouter · ✓ Jun 2026 | TEXTCODE | Free API | Solid~ Medium | 20 RPM · 50-1000 RPD | ✓ no card · ✓ commercial | ||
| 14 | Qwen · ✓ Jun 2026 | CODETEXT | Free API | Strong | Free tier | ✓ no card · ? comm | ||
| 15 |  Scaleway · ✓ Jun 2026 | CODETEXT | Free API | Strong | Free tier | ✓ no card · ? comm | ||
| 16 |  NVIDIA NIM · ✓ Jun 2026 | IMAGEVIDEOAUDIOTEXT | Free API | unrated | ~40 RPM | ✓ no card · ? comm | ||
| 17 |  Tencent (via OpenRouter) · ✓ Jul 2026 | TEXTCODE | Free API | Frontier~ Medium | Free for ~2 weeks from 2026-07-07 via OpenRouter (tencent/hy3:free); standard OpenRouter rate limits apply | ✓ no card · ✓ commercial | ||
| 18 |  NVIDIA NIM · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 19 | NVIDIA NIM · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 20 | OpenCode Zen · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 21 | GitHub Models · ✓ Jun 2026 | CODETEXT | Free API | Solid | Free tier | ✓ no card · ? comm | ||
| 22 |  OVHcloud AI Endpoints · ✓ Jun 2026 | TEXT | Free API | unrated | 2 RPM (anonymous) | ✓ no card · ? comm | ||
| 23 | OpenCode Zen · ✓ Jun 2026 | CODETEXT | Free API | Frontier | Free tier | ✓ no card · ? comm | ||
| 24 | Google Gemini · ✓ Jul 2026 | IMAGEVIDEOAUDIOTEXT | Free API | unrated | 10 RPM · 500 RPD | ✓ no card · ? comm | ||
| 25 |  Groq · ✓ Jul 2026 | TEXTCODE | Free API | Strong⚡⚡ Blazing | 1,000 RPD · 30 RPM | ✓ no card · ✓ commercial |
Need more than a free tier?
We wire free-tier and open-weight models into production stacks: multi-provider failover, cost caps, evals against your real inputs. Free 30-minute call, no pitch deck.
Book a free callBrowse all 294 free models by provider
Aion Labs
Black Forest Labs
Cerebras
Cloudflare Workers AI
- @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
- @cf/google/gemma-4-26b-a4b-it
- @cf/meta/llama-3.3-70b-instruct-fp8-fast
- @cf/meta/llama-4-scout-17b-16e-instruct
- @cf/mistralai/mistral-small-3.1-24b-instruct
- @cf/moonshotai/kimi-k2.7-code
- @cf/openai/gpt-oss-120b
- @cf/zhipuai/glm-4.7-flash
- + 42 more models
- GLM-4.7-Flash
- GPT OSS 20B
- Granite 4.0 Micro
- Kimi K2.6
- Mistral 7B v0.2
- Nemotron 3 Super
- Qwen2.5 Coder 32B
- Qwen3 30B MoE
DeepSeek
ElevenLabs
GitHub Models
- + 35 more models
- Codestral 2501
- DeepSeek V3 0324
- DeepSeek-R1
- gpt-4.1
- GPT-4.1 Nano
- gpt-4.1-mini
- gpt-4o
- gpt-5
- Llama 3.1 405B
- Llama 3.1 8B
- Llama 3.2 11B Vision
- Llama 3.2 90B Vision
- Llama 3.3 70B
- Llama 4 Maverick
- Llama 4 Scout
- Llama-4-Maverick-17B-128E
- Meta-Llama-3.3-70B
- Ministral 3B
- Mistral Medium 2505
- Mistral Small 2503
- Mistral-Small-3.1
- o4-mini
Google AI Studio
Groq
Hugging Face
Kilo Code
LLM7.io
Mistral AI
Mistral Codestral
NVIDIA
NVIDIA NIM
- + 90 more models
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- deepseek-ai/deepseek-r1
- Gemma 4 31B
- GLM 5.1
- google/gemma-4-31b
- GPT OSS 120B
- GPT OSS 20B
- Kimi K2.6
- Llama 3.2 11B Vision
- Llama 4 Maverick
- meta/llama-3.1-405b-instruct
- MiniMax M2.7
- MiniMax M3
- minimax/minimax-m2.7
- Ministral 14B
- Mistral Large 675B
- Mistral Medium 3.5
- Mistral Small 4
- mistralai/mistral-large-2-instruct
- Nemotron 3 Omni
- Nemotron 3 Ultra
- nvidia/llama-3.1-nemotron-ultra-253b-v1
- nvidia/nemotron-3-nano-30b-a3b
- nvidia/nemotron-3-super-120b-a12b
- Phi 4 Mini
- qwen/qwen2.5-72b-instruct
- Qwen3 80B Instruct
- Qwen3.5 122B
- Qwen3.5 400B VLM
- Seed OSS 36B
- Step 3.5 Flash
- Step 3.7 Flash
- Stockmark 100B
Ollama Cloud
- + 30 more cloud models
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- deepseek-r1:cloud
- deepseek-v3.1:671b-cloud
- Devstral 2 123B
- Gemma 4 31B
- GLM 4.7
- GLM 5.1
- glm-4.6:cloud
- GPT OSS 120B
- GPT OSS 20B
- gpt-oss:120b-cloud
- Kimi K2.6
- kimi-k2:1t-cloud
- MiniMax M2.7
- MiniMax M3
- Mistral Large 3
- Nemotron 3 Super
- Nemotron 3 Ultra
- Qwen3 Coder 480B
- Qwen3 Coder Next
- qwen3-coder:480b-cloud
- Qwen3.5 397B
OpenAI
OpenRouter
- :free models
- + ~12 more free models
- Arcee Trinity Large
- Dolphin Mistral 24B
- Gemma 4 26B MoE
- GLM 4.5 Air
- google/gemma-4-31b-it:free
- Kimi K2.6
- LFM 2.5 1.2B
- LFM 2.5 Thinking
- Llama 3.2 3B
- meta-llama/llama-3.3-70b-instruct:free
- Nemotron 3 Omni
- Nemotron Nano 12B VL
- Nemotron Nano 30B
- Nemotron Nano 9B
- nousresearch/hermes-3-llama-3.1-405b:free
- nvidia/nemotron-3-super-120b-a12b:free
- nvidia/nemotron-3-ultra-550b-a55b:free
- openai/gpt-oss-120b:free
- openai/gpt-oss-20b:free
- OpenRouter Free
- Owl Alpha
- Poolside Laguna XS.2
- poolside/laguna-m.1:free
- qwen/qwen3-coder:free
- qwen/qwen3-next-80b-a3b-instruct:free
OVHcloud
OVHcloud AI Endpoints
Pollinations.ai
Qwen
Routeway
SambaNova
Scaleway
Stability AI
Tencent (via OpenRouter)
Z AI (Zhipu AI)
Z.ai
Free monthly update
The monthly free-models update
What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.
Free AI models, honestly answered
Are free AI models really free?
Three kinds of free exist: open-weight models you self-host (free forever, you pay only infrastructure), permanent free API tiers (free within rate limits), and no-signup tools. The catch is usually rate limits, non-commercial clauses, or your data being used for training. Every listing here shows its catch.
What is the best free AI model right now?
It depends on the job: the community votes on this page rank what practitioners actually rate highest, and you can filter by text, code, image, video, audio, or embeddings. For raw quality per dollar, open-weight frontier models you self-host are hard to beat.
Can I use free AI models commercially?
Often yes for permissive open-weight licenses (Apache-2.0, MIT), but many free API tiers prohibit commercial use and some community licenses add revenue caps. Check the commercial column on each listing and verify the current license before shipping.
Do free AI API keys without signup exist?
Yes, a small set of services work with no key at all, and they are labeled No-signup here. Never use shared API keys posted online: they run on someone else's billing, violate provider terms, and get revoked.
How do I use a free model in my own project?
Most free API tiers are OpenAI-compatible, so you point your SDK at the provider base URL with your free key. Every listing has a How drawer with setup steps, a quickstart snippet, and a copy-paste prompt that walks Claude Code through the setup for you.
Free model guides
- Full AI Model Leaderboard — paid and free, benchmarks and speed
- Live AI Model Pricing Index
- Free AI models for coding — Cursor, VS Code, Claude Code (2026)
- Best free AI models for n8n — no-token agent workflows (2026)
- Free AI models for commercial use — license-safe options (2026)
- Best local LLM tools — run models locally in 2026
Wiring one of these into a production workflow instead of a script? Our n8n automation agency builds and maintains the automation around the model.
How we rank & verify. Listings are ordered by community upvotes (one vote per model per device, no login); ties fall back to our performance estimate. Performance is a composite estimate from public benchmarks (LMArena, SWE-bench, MTEB) and provider specs; unknowns are marked “unrated”. “Free” claims and limits are re-checked periodically and dated per row.
Sources. Seeded and cross-checked against mnfst/awesome-free-llm-apis · zebbern/no-cost-ai · 12britz/awesome-free-models · vava-nessa/free-coding-models · open-free-llm-api · cheahjs/free-llm-api-resources. We never list or link shared API keys.