Free LLM Hub

Free models, API limits, and install guides

Catalog of free large language models: hosted APIs, local runtimes, rate limits, and step-by-step install guides.

Last updated: 2026-10-10

Free API limits compared · Free Llama API · Free API in VS Code · Fallback when a limit hits · Deals

Hot right now

All deals

Models

Model Free API Ollama Context Use Updated
Apodex 1.1 Mini openrouter-free — 262k reasoning, coding 2026-10-10
Codestral mistral-free codestral 33k coding 2026-10-10
Command R — command-r 131k general —
DeepSeek Coder V2 — deepseek-coder-v2 164k coding —
DeepSeek R1 — deepseek-r1 128k reasoning, coding —
Devstral — devstral 131k coding —
Dots3-Note Preview openrouter-free — 512k reasoning, coding, general 2026-10-10
Gemini 2.5 Flash gemini-free — 1000k general, coding, vision 2026-10-10
Gemini 3.8 Flash gemini-free — 1000k general, coding, vision 2026-10-10
Gemma 3 — gemma3 131k general, vision —
Gemma 4 openrouter-free gemma2 262k general 2026-10-10
Gemma 4 31B openrouter-free — 262k general, coding 2026-10-10
GLM-5 — — 256k general, coding, reasoning 2026-10-10
GLM-5.3 Flash — — 1049k general, coding, reasoning 2026-10-10
GPT-OSS groq gpt-oss 131k reasoning, coding 2026-10-10
Granite 4 — granite4 131k general, coding —
Hermes 3 — hermes3 131k general, coding —
Hy4 Preview — — 1049k general, coding, reasoning —
Inkling openrouter-free — 1049k general, reasoning 2026-10-10
Inkling Small openrouter-free — 1049k general, reasoning 2026-10-10
K2 Horizon 7B — — 524k general, coding, reasoning —
Laguna S 2.1 openrouter-free — 262k general, coding 2026-10-10
Laguna XS 2.1 openrouter-free — 262k general, coding 2026-10-10
LFM 2.5 openrouter-free — 66k general 2026-10-10
Ling 3.0 Flash Sante openrouter-free — 262k reasoning, general 2026-10-10
Ling 3.1 Flash openrouter-free — 262k reasoning, coding, general 2026-10-10
Llama 3.1 cloudflare-workers-ai llama3.1 128k general, coding 2026-10-10
Llama 3.2 — llama3.2 128k general —
Llama 3.2 Vision — llama3.2-vision 131k vision, general —
Llama 3.3 cloudflare-workers-ai llama3.3 128k general, coding 2026-10-10
LLaVA — llava 4k vision —
MiniMax M2.7 — — 197k general, coding 2026-10-10
MiniMax M3 — — 1049k general, coding, reasoning 2026-10-10
Mistral — mistral 33k general —
Mistral Nemo mistral-free mistral-nemo 131k general, coding 2026-10-10
Mixtral 8x7B — mixtral 33k general, coding —
Nemotron 3 openrouter-freenvidia-nim — 256k general, coding, reasoning 2026-10-10
Nemotron 3 Super openrouter-free — 262k general, coding 2026-10-10
Nemotron 3 Ultra openrouter-free — 1000k general, coding, reasoning 2026-10-10
Nemotron 3.5 Content Safety openrouter-free — 128k general 2026-10-10
Nemotron 3.5 Lightning openrouter-free — 1000k general, coding 2026-10-10
Nex-N2.5 Mini — — 262k coding, general 2026-10-10
Nex-N2.5 Pro — — 262k coding, general, reasoning 2026-10-10
North Mini Code openrouter-free — 256k coding 2026-10-10
OLMo 2 — olmo2 4k general —
Phi-3 — phi3 131k general, reasoning —
Phi-4 — phi4 16k coding, reasoning —
Qwen 2.5 cloudflare-workers-ai qwen2.5 33k general, coding 2026-10-10
Qwen2.5 Coder — qwen2.5-coder 33k coding —
Qwen3 — qwen3 33k general, coding —
Qwen3 Coder — qwen3-coder 262k coding —
Qwen3.8 27B groq qwen3.8:27b 262k coding, reasoning, vision, general 2026-10-10
QwQ — qwq 41k reasoning —
SmolLM2 — smollm2 8k general —

Limits checked against official docs on 2026-10-10. Rates change without notice. Not affiliated with providers unless noted. Verify before production use.

Full API comparison · Groq limits · Gemini free models