# Free LLM APIs

Models with at least one free-tier (zero-price, non-subscription) offer. Prices as of 2026-11-22, USD per 1M tokens.

Models ranked by how many providers list a free tier. Top 20 of 75.

| # | Model | Free on | Cheapest paid output |
| --- | --- | --- | --- |
| 1 | [Gemma 4 31B IT](https://sovyron.com/models/gemma-4-31b-it/) | AIHubMix, AMD, Bothub, Google, Nvidia, QVAC, Requesty, UnoRouter | $0.25 |
| 2 | [GLM-4.7-Flash](https://sovyron.com/models/glm-4-7-flash/) | AIHubMix, EmpirioLabs AI, Hugging Face, Kenari, Pendra, Z.AI, ZenMux, Zhipu AI | $0.4 |
| 3 | [Nemotron 3 Ultra 550B A55B](https://sovyron.com/models/nemotron-3-ultra-550b-a55b/) | AIHubMix, InferAll, Kenari, Nvidia, Requesty, UnoRouter | $0.1 |
| 4 | [GLM-5.3-Flash](https://sovyron.com/models/glm-5-3-flash/) | AIHubMix, AMD, InferAll, Nvidia, OrcaRouter | $0.0185 |
| 5 | [DeepSeek V4 Flash](https://sovyron.com/models/deepseek-v4-flash/) | InferX, Obscurify.ai, OrcaRouter, Pendra, SenseNova (China) | $0.132 |
| 6 | [Nemotron 3.5 Lightning 30B A3B](https://sovyron.com/models/nemotron-3-5-lightning-30b-a3b/) | AIHubMix, InferAll, Merge Gateway, Nvidia, Requesty | $0.096 |
| 7 | [GLM-4.6V-Flash](https://sovyron.com/models/glm-4-6v-flash/) | EmpirioLabs AI, Kenari, Z.AI, ZenMux, Zhipu AI | $0.9 |
| 8 | [DeepSeek V4.1 Flash](https://sovyron.com/models/deepseek-v4-1-flash/) | AMD, Nvidia, OpenCode, SenseNova (China) | $0.12 |
| 9 | [GPT OSS 20B](https://sovyron.com/models/gpt-oss-20b/) | InferAll, LMStudio, Nvidia, QVAC | $0.075 |
| 10 | [Nemotron 3.5 Lightning](https://sovyron.com/models/nemotron-3-5-lightning/) | Kilo Gateway, OpenCode, OpenRouter, Vercel AI Gateway | $0.2 |
| 11 | [GLM-5.3](https://sovyron.com/models/glm-5-3/) | AIHubMix, InferAll, TokenRouter | $0.7013 |
| 12 | [Kimi K3](https://sovyron.com/models/kimi-k3/) | Kimi For Coding (kimi.com), Kimi For Coding (kimi.ai), SenseNova (China) | $4.5 |
| 13 | [Qwen3.8 27B](https://sovyron.com/models/qwen3-8-27b/) | AMD, Hetzner, IteraCompute | $0.32 |
| 14 | [Gemma 4 26B A4B IT](https://sovyron.com/models/gemma-4-26b-a4b-it/) | AIHubMix, Google, NaN | $0.19 |
| 15 | [Hy4 flash](https://sovyron.com/models/hy4-flash/) | Kenari, OpenCode, OpenCode Go | $0.1405 |
| 16 | [Muse Glimmer 30B](https://sovyron.com/models/muse-glimmer-30b/) | Kenari, Nvidia, Requesty | $0.32 |
| 17 | [Nemotron 3.5 Super VL](https://sovyron.com/models/nemotron-3-5-super-vl/) | Kilo Gateway, OpenCode, OpenRouter | $0.35 |
| 18 | [Nemotron 3 Ultra](https://sovyron.com/models/nemotron-3-ultra/) | Bothub, Kilo Gateway, OpenRouter | $1.7 |
| 19 | [LongCat 2.5](https://sovyron.com/models/longcat-2-5/) | Kenari, OpenCode, OpenCode Go | $1.2 |
| 20 | [Nemotron 3 Nano Omni](https://sovyron.com/models/nemotron-3-nano-omni/) | Kilo Gateway, Nvidia, OpenRouter | $0.9 |

HTML page: https://sovyron.com/cheapest/free-llm-apis/
Methodology: https://sovyron.com/methodology/#blend
