Free LLM API models (17)
Every model below costs $0 for both input and output tokens via OpenRouter. Perfect for prototyping, hobby projects, and high-volume low-stakes workloads. Free tiers usually have rate limits and may use your prompts for training — check each provider's terms. Verified 2026-10-21.
| Price | |||
|---|---|---|---|
| Thinking Machines: Inkling (free) thinkingmachines/inkling:free | 1.0M | 262K | FREE |
| Thinking Machines: Inkling Small (free) thinkingmachines/inkling-small:free | 1.0M | 262K | FREE |
| NVIDIA: Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free | 1M | 66K | FREE |
| NVIDIA: Nemotron 3.5 Lightning (free) nvidia/nemotron-3.5-lightning:free | 1M | 66K | FREE |
| NVIDIA: Nemotron 3.5 Super VL (free) nvidia/nemotron-3.5-super-vl:free | 1M | 131K | FREE |
| MiniMax: MiniMax M3.1 Flash (free) minimax/minimax-m3.1-flash:free | 1M | 524K | FREE |
| Dots Studio: Dots3-Note Preview (free) dots-studio/dots-3-note-preview:free | 512K | 461K | FREE |
| NVIDIA: Nemotron 3 Super (free) nvidia/nemotron-3-super-120b-a12b:free | 262K | 236K | FREE |
| Google: Gemma 4 31B (free) google/gemma-4-31b-it:free | 262K | 33K | FREE |
| Google: Gemma 4 26B A4B (free) google/gemma-4-26b-a4b-it:free | 262K | 33K | FREE |
| Poolside: Laguna XS 2.1 (free) poolside/laguna-xs-2.1:free | 262K | 33K | FREE |
| Poolside: Laguna S 2.1 (free) poolside/laguna-s-2.1:free | 262K | 33K | FREE |
| XingChen: Xing4.0 29B A4B (free) xingchen-agi/xing4.0-29b-a4b:free | 262K | 236K | FREE |
| NVIDIA: Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 256K | 66K | FREE |
| Cohere: North Mini Code (free) cohere/north-mini-code:free | 256K | 64K | FREE |
| NVIDIA: Nemotron 3.5 Content Safety (free) nvidia/nemotron-3.5-content-safety:free | 128K | 8K | FREE |
| LiquidAI: LFM2.5-2.6B (free) liquid/lfm-2.5-2.6b:free | 66K | 8K | FREE |
How to use a free model (3 steps)
- 1. Get an API key. Create a free OpenRouter account — no credit card needed for free models.
- 2. Point your request at OpenRouter. The base URL is
https://openrouter.ai/api/v1/chat/completions(OpenAI-compatible — any existing SDK works, just change the base URL and key). - 3. Pick a model ID from the table above. Example with curl:
curl https://openrouter.ai/api/v1/chat/completions \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "thinkingmachines/inkling-small:free", "messages": [{"role": "user", "content": "Hello!"}] }'
Rate limits: ~50 requests/day without credits, 1,000/day after buying any amount of credits once.
When should you use free models?
- Prototyping — validate your app before spending a cent
- High-volume classification/extraction — where quality bar is low
- Learning & experiments — zero-risk API practice
When you outgrow free tiers, check the cost calculator to find the cheapest paid model for your workload — often just a few dollars a month.