Models are included when both prompt and completion prices are reported as zero. Free model availability and limits can change, so verify before production use.
Free LLM API Models
This page lists models with both prompt and completion price reported as zero, useful for experiments, prototypes, and early evaluation.
46Models listed
1M input + 500K outputCost example tokens
USD / 1MNormalized prices
Quick shortlist
Start with Ox Alpha.
This guide starts with zero-price models for experiments and prototypes; verify limits before production use.
The ranking is a discovery aid, not a final recommendation. Always compare the model against your workload and verify provider pricing before production use.
Model Ranking
Browse all models| Model | Provider | Prompt | Output | Sample cost | Your Cost | Context | Popularity | Release |
|---|---|---|---|---|---|---|---|---|
| New🔥Ox Alpha | stealth | $0 | $0 | $0 | $0 | 1.05M | #4 | |
| 🔥Nemotron 3 Ultra (free) | NVIDIA | $0 | $0 | $0 | $0 | 1M | #7 | |
| 🔥Laguna S 2.1 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | #11 | |
| New🔥Nemotron 3.5 Lightning (free) | NVIDIA | $0 | $0 | $0 | $0 | 1M | #17 | |
| NewDots3-Note Preview (free) | Dots Studio | $0 | $0 | $0 | $0 | 512K | ||
| NewLFM2.5-2.6B (free) | LiquidAI | $0 | $0 | $0 | $0 | 65.54K | ||
| Ling 3.0 Tiny (free) | inclusionAI | $0 | $0 | $0 | $0 | 262.14K | ||
| Inkling Small (free) | Thinking Machines | $0 | $0 | $0 | $0 | 262.14K | ||
| Ling-3.0-flash (free) | inclusionAI | $0 | $0 | $0 | $0 | 262.14K | ||
| Inkling (free) | Thinking Machines | $0 | $0 | $0 | $0 | 262.14K | ||
| Hy3 (free) | Tencent | $0 | $0 | $0 | $0 | 262.14K | ||
| Laguna XS 2.1 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | ||
| North Mini Code (free) | Cohere | $0 | $0 | $0 | $0 | 256K | ||
| GLM 5.2 (free) | Z.ai | $0 | $0 | $0 | $0 | 256K | ||
| Kimi K2.7 Code (free) | MoonshotAI | $0 | $0 | $0 | $0 | 262.14K | ||
| Nex-N2-Pro (free) | Nex AGI | $0 | $0 | $0 | $0 | 262.14K | ||
| Nemotron 3.5 Content Safety (free) | NVIDIA | $0 | $0 | $0 | $0 | 128K | ||
| CoBuddy (free) | Baidu Qianfan | $0 | $0 | $0 | $0 | 131.07K | ||
| Owl Alpha | OpenRouter | $0 | $0 | $0 | $0 | 1.05M | ||
| Nemotron 3 Nano Omni (free) | NVIDIA | $0 | $0 | $0 | $0 | 256K | ||
| Laguna XS.2 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | ||
| Laguna M.1 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | ||
| DeepSeek V4 Flash (free) | DeepSeek | $0 | $0 | $0 | $0 | 1.05M | ||
| Kimi K2.6 (free) | MoonshotAI | $0 | $0 | $0 | $0 | 262.14K | ||
| Gemma 4 26B A4B (free) | $0 | $0 | $0 | $0 | 262.14K | |||
| Gemma 4 31B (free) | $0 | $0 | $0 | $0 | 262.14K | |||
| Trinity Large Thinking (free) | Arcee AI | $0 | $0 | $0 | $0 | 262.14K | ||
| Lyria 3 Pro Preview | $0 | $0 | $0 | $0 | 1.05M | |||
| Lyria 3 Clip Preview | $0 | $0 | $0 | $0 | 1.05M | |||
| Nemotron 3 Super (free) | NVIDIA | $0 | $0 | $0 | $0 | 262.14K | ||
| MiniMax M2.5 (free) | MiniMax | $0 | $0 | $0 | $0 | 204.8K | ||
| Free Models Router | OpenRouter | $0 | $0 | $0 | $0 | 200K | ||
| LFM2.5-1.2B-Thinking (free) | LiquidAI | $0 | $0 | $0 | $0 | 32.77K | ||
| LFM2.5-1.2B-Instruct (free) | LiquidAI | $0 | $0 | $0 | $0 | 32.77K | ||
| Nemotron 3 Nano 30B A3B (free) | NVIDIA | $0 | $0 | $0 | $0 | 256K | ||
| Nemotron Nano 12B 2 VL (free) | NVIDIA | $0 | $0 | $0 | $0 | 128K | ||
| Qwen3 Next 80B A3B Instruct (free) | Qwen | $0 | $0 | $0 | $0 | 262.14K | ||
| Nemotron Nano 9B V2 (free) | NVIDIA | $0 | $0 | $0 | $0 | 128K | ||
| gpt-oss-120b (free) | OpenAI | $0 | $0 | $0 | $0 | 131.07K | ||
| gpt-oss-20b (free) | OpenAI | $0 | $0 | $0 | $0 | 131.07K | ||
| GLM 4.5 Air (free) | Z.ai | $0 | $0 | $0 | $0 | 131.07K | ||
| Qwen3 Coder 480B A35B (free) | Qwen | $0 | $0 | $0 | $0 | 1.05M | ||
| Uncensored (free) | Venice | $0 | $0 | $0 | $0 | 32.77K | ||
| Llama 3.3 70B Instruct (free) | Meta | $0 | $0 | $0 | $0 | 131.07K | ||
| Llama 3.2 3B Instruct (free) | Meta | $0 | $0 | $0 | $0 | 131.07K | ||
| Hermes 3 405B Instruct (free) | Nous | $0 | $0 | $0 | $0 | 131.07K |
Pricing FAQ
How is the sample workload cost calculated?
The sample workload uses 1,000,000 input tokens plus 500,000 output tokens, then applies each model's normalized USD price per 1 million tokens.
Why do input and output token prices matter separately?
Many applications are output-token heavy, while retrieval and classification workloads may be input-token heavy. Comparing both prices helps avoid picking a model that is cheap for the wrong workload shape.
Should I verify prices before production use?
Yes. AI Model Matrix normalizes public pricing metadata for comparison, but provider availability, limits, and prices can change. Always verify the final contract or provider dashboard before production use.
Related Guides
Cheapest LLM APIs
Sort models by estimated workload cost and normalized token prices.
Open guideLargest Context Windows
Find models for long documents, retrieval, and codebase context.
Open guideCoding Models
Compare code-oriented models by cost, context, and practical popularity signals.
Open guideFree Models
Browse zero-price models for prototypes and evaluation.
Open guideRAG Models
Start from large context windows and practical input-cost constraints.
Open guideChatbot Costs
Find budget-sensitive models for output-heavy assistant traffic.
Open guideCost Calculator
Enter your own input and output token volume before narrowing the shortlist.
Estimate costAlternatives
Find cheaper candidates around popular model anchors.
Find alternatives