LLMs with a genuinely free tier
Poolside: Laguna XS 2.1 is the cheapest option at $0.060 per million input tokens. Models available at no cost, usually with rate limits and no uptime guarantee. Good for prototypes, risky for production.
19 models qualify
Ranked by blended cost - input weighted 75%, output 25%.
| # | Model | Blended / 1M | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|---|---|
| 1 | Flint (free) Recursive | Free | Free | Free | 262K | Free tierReasoningToolsOpen weights |
| 2 | Xing4.0 29B A4B (free) XingChen | Free | Free | Free | 262K | Free tierReasoningToolsOpen weights |
| 3 | Dots3-Note Preview (free) Dots Studio | Free | Free | Free | 512K | Free tierReasoningToolsVision |
| 4 | North Mini Code (free) Cohere | Free | Free | Free | 256K | Free tierReasoningToolsOpen weights |
| 5 | Free | Free | Free | 256K | Free tierReasoningToolsVisionOpen weights | |
| 6 | Lyria 3 Pro Preview | Free | Free | Free | 1.0M | Free tierVision |
| 7 | Lyria 3 Clip Preview | Free | Free | Free | 1.0M | Free tierVision |
| 8 | Free Models Router OpenRouter | Free | Free | Free | 200K | Free tierReasoningToolsVision |
| 9 | Laguna XS 2.1 Poolside | $0.075 | $0.060 | $0.120 | 262K | Free tierReasoningToolsOpen weights |
| 10 | Nemotron 3.5 Lightning NVIDIA | $0.103 | $0.070 | $0.200 | 262K | Free tierReasoningToolsOpen weights |
| 11 | Laguna S 2.1 Poolside | $0.113 | $0.090 | $0.180 | 1.0M | Free tierReasoningToolsOpen weights |
| 12 | Gemma 4 26B A4B | $0.143 | $0.090 | $0.300 | 262K | Free tierReasoningToolsVisionOpen weights |
| 13 | $0.200 | $0.200 | $0.200 | 131K | Free tierReasoningVisionOpen weights | |
| 14 | Nemotron 3.5 Super VL NVIDIA | $0.237 | $0.150 | $0.500 | 1.0M | Free tierReasoningToolsVisionOpen weights |
| 15 | Gemma 4 31B | $0.250 | $0.200 | $0.400 | 262K | Free tierReasoningToolsVisionOpen weights |
| 16 | LFM2.5-2.6B Liquid AI | $0.387 | $0.350 | $0.500 | 128K | Free tierReasoningToolsOpen weights |
| 17 | Inkling Small Thinking Machines | $0.637 | $0.450 | $1.20 | 524K | Free tierReasoningToolsVisionOpen weights |
| 18 | Nemotron 3 Ultra NVIDIA | $1.05 | $0.600 | $2.40 | 262K | Free tierReasoningToolsOpen weights |
| 19 | Inkling Thinking Machines | $1.76 | $1.00 | $4.05 | 524K | Free tierReasoningToolsVisionOpen weights |
Frequently asked
What is the cheapest LLM for zero-cost usage?
Poolside: Laguna XS 2.1 at $0.060 per million input tokens and $0.120 per million output tokens, with a 262K token context window.
How many models qualify for zero-cost usage?
19 of the 359 models tracked here meet the criteria for this list.
How much do prices vary within this category?
By roughly 24×, from Laguna XS 2.1 at the bottom to Inkling at the top.