Docs · Guides · Reference

Docs

Learn it once.

Short guides with real commands. No fluff, no 40-minute videos.

Guide · updated 2026-09-26

Free models

The 13-model free pool, the auto-router, and how to pick.

Seventeen open models at $0 each, plus an auto-router and a keyless baseline — nineteen free ways to get an answer.

What is in the pool

Qwen 3.8 27B, both Gemma 4 sizes, Nemotron Lightning, Nano, Super and Ultra, both Poolside Laguna code specialists, GLM 5.2, Dots 3, both Ling Flash flavors, LFM 2.5, and both Inkling models, Cohere North Mini Code — plus a keyless baseline that answers even when every provider is busy. The workbench, chat, CLI, and desktop app all read the same live catalog from GET /api/models.php, so new models appear everywhere at once.

Auto-router first

Leave the picker on the default and requests ride openrouter/free: the best $0 model available right now. If it stumbles, the pool retries siblings automatically (up to 4 attempts), then falls back to the keyless baseline. Pick a specific model only when you want consistent behavior for a repeated task.

Every free model

ModelProvider · best for · API id
Auto-routerRareMatter · Default pick — best $0 model now openrouter/free
GPT-OSS 20BKeyless baseline · Answers when providers are busy openai-fast
Qwen 3.8 27BAlibaba · Chat, writing, light code qwen/qwen3.8-27b:free
Gemma 4 31B / 26BGoogle · Analysis (31B) and everyday speed (26B) google/gemma-4-31b-it:free
Nemotron LightningNvidia · Fast drafts and iterations nvidia/nemotron-3.5-lightning:free
Nemotron NanoNvidia · Compact step-by-step reasoning nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Nemotron Super 120BNvidia · Hard multi-step problems nvidia/nemotron-3-super-120b-a12b:free
Nemotron Ultra 550BNvidia · Biggest free model, heavy lifts nvidia/nemotron-3-ultra-550b-a55b:free
Laguna S / XSPoolside · Code generation and debugging poolside/laguna-s-2.1:free
GLM 5.2Z.ai · All-round chat and writing z-ai/glm-5.2:free
Dots 3 NoteDots Studio · Summaries, structured writing dots-studio/dots-3-note-preview:free
Ling Flash / SanteInclusionAI · Snappy chat answers inclusionai/ling-3.0-flash-fin:free
LFM 2.5Liquid · Tiny and instant liquid/lfm-2.5-2.6b:free
North Mini CodeCohere · Quick code edits and reviews cohere/north-mini-code:free
Inkling / SmallThinking Machines · Natural back-and-forth chat thinkingmachines/inkling:free

Browse with pictures on the models page.

Proof on every reply

Each answer labels its exact model and path — sponsored for site-key $0 calls, free for the keyless baseline, your_key when your own provider key paid. If a label ever surprises you, the troubleshooting guide explains why.