Free LLM Models Token API
These models offer completely free usage with no token costs for both input and output via OpenRouter API. Perfect for experimentation, development, and testing.
Free Models
59
Available at no cost
Providers
19
Offering free models
Last Updated
Just now
Auto-refreshes every 12 hours
Available Free Models
All models listed below have zero cost for both input and output tokens
| Provider | Model | Context | Pricing |
|---|---|---|---|
'%3e%3cpath%20d='M3%20248.945C18%20248.945%2076%20236%20106%20219C136%20202%20136%20202%20198%20158C276.497%20102.293%20332%20120.945%20423%20120.945'%20stroke-width='90'%20/%3e%3cpath%20d='M511%20121.5L357.25%20210.268L357.25%2032.7324L511%20121.5Z'%20/%3e%3cpath%20d='M0%20249C15%20249%2073%20261.945%20103%20278.945C133%20295.945%20133%20295.945%20195%20339.945C273.497%20395.652%20329%20377%20420%20377'%20stroke-width='90'%20/%3e%3cpath%20d='M508%20376.445L354.25%20287.678L354.25%20465.213L508%20376.445Z'%20/%3e%3c/g%3e%3c/svg%3e) openrouter | Sonoma Dusk Alpha openrouter/sonoma-dusk-alpha | 2.0M | FREE |
| openrouter | Sonoma Sky Alpha openrouter/sonoma-sky-alpha | 2.0M | FREE |
 Gemini | Google: Gemini 2.0 Flash Experimental (free) google/gemini-2.0-flash-exp:free | 1.0M | FREE |
 Qwen | Qwen: Qwen3 Coder 480B A35B (free) qwen/qwen3-coder:free | 262K | FREE |
 DeepSeek | DeepSeek: R1 0528 (free) deepseek/deepseek-r1-0528:free | 164K | FREE |
| DeepSeek | DeepSeek: DeepSeek V3 0324 (free) deepseek/deepseek-chat-v3-0324:free | 164K | FREE |
| DeepSeek | DeepSeek: R1 (free) deepseek/deepseek-r1:free | 164K | FREE |
tngtech | TNG: DeepSeek R1T2 Chimera (free) tngtech/deepseek-r1t2-chimera:free | 164K | FREE |
tngtech | TNG: DeepSeek R1T Chimera (free) tngtech/deepseek-r1t-chimera:free | 164K | FREE |
%20--%3e%3csvg%20version='1.1'%20id='Layer_1'%20xmlns='http://www.w3.org/2000/svg'%20xmlns:xlink='http://www.w3.org/1999/xlink'%20x='0px'%20y='0px'%20viewBox='0%200%20129%20129'%20style='enable-background:new%200%200%20129%20129;'%20xml:space='preserve'%3e%3cstyle%20type='text/css'%3e%20.st0{fill:%23F25022;}%20.st1{fill:%237FBA00;}%20.st2{fill:%2300A4EF;}%20.st3{fill:%23FFB900;}%20%3c/style%3e%3cpath%20class='st0'%20d='M0,0h61.3v61.3H0V0z'/%3e%3cpath%20class='st1'%20d='M67.7,0H129v61.3H67.7V0z'/%3e%3cpath%20class='st2'%20d='M0,67.7h61.3V129H0V67.7z'/%3e%3cpath%20class='st3'%20d='M67.7,67.7H129V129H67.7V67.7z'/%3e%3c/svg%3e) Microsoft | Microsoft: MAI DS R1 (free) microsoft/mai-ds-r1:free | 164K | FREE |
 NVIDIA | NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 (free) nvidia/llama-3.1-nemotron-ultra-253b-v1:free | 131K | FREE |
| Qwen | Qwen: Qwen3 235B A22B (free) qwen/qwen3-235b-a22b:free | 131K | FREE |
 MoonshotAI | MoonshotAI: Kimi Dev 72B (free) moonshotai/kimi-dev-72b:free | 131K | FREE |
| MoonshotAI | MoonshotAI: Kimi VL A3B Thinking (free) moonshotai/kimi-vl-a3b-thinking:free | 131K | FREE |
nousresearch | Nous: DeepHermes 3 Llama 3 8B Preview (free) nousresearch/deephermes-3-llama-3-8b-preview:free | 131K | FREE |
| DeepSeek | DeepSeek: Deepseek R1 0528 Qwen3 8B (free) deepseek/deepseek-r1-0528-qwen3-8b:free | 131K | FREE |
 GPT | OpenAI: gpt-oss-20b (free) openai/gpt-oss-20b:free | 131K | FREE |
'%3e%3cpath%20d='M54.3219%200H27.1528V27.0892H54.3219V0Z'%20fill='%23FFD800'/%3e%3cpath%20d='M162.984%200H135.815V27.0892H162.984V0Z'%20fill='%23FFD800'/%3e%3cpath%20d='M81.482%2027.0913H27.1528V54.1805H81.482V27.0913Z'%20fill='%23FFAF00'/%3e%3cpath%20d='M162.99%2027.0913H108.661V54.1805H162.99V27.0913Z'%20fill='%23FFAF00'/%3e%3cpath%20d='M162.971%2054.168H27.1528V81.2572H162.971V54.168Z'%20fill='%23FF8205'/%3e%3cpath%20d='M54.3219%2081.2593H27.1528V108.349H54.3219V81.2593Z'%20fill='%23FA500F'/%3e%3cpath%20d='M108.661%2081.2593H81.4917V108.349H108.661V81.2593Z'%20fill='%23FA500F'/%3e%3cpath%20d='M162.984%2081.2593H135.815V108.349H162.984V81.2593Z'%20fill='%23FA500F'/%3e%3cpath%20d='M81.4879%20108.339H-0.00146484V135.429H81.4879V108.339Z'%20fill='%23E10500'/%3e%3cpath%20d='M190.159%20108.339H108.661V135.429H190.159V108.339Z'%20fill='%23E10500'/%3e%3c/g%3e%3cdefs%3e%3cclipPath%20id='clip0_173_337'%3e%3crect%20width='190.141'%20height='135'%20fill='white'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e) Mistral | Mistral: Mistral Small 3.2 24B (free) mistralai/mistral-small-3.2-24b-instruct:free | 131K | FREE |
| Mistral | Mistral: Mistral Nemo (free) mistralai/mistral-nemo:free | 131K | FREE |
'%3e%3cpath%20d='M137.381%200H22.619C10.1269%200%200%2010.1269%200%2022.619V137.381C0%20149.873%2010.1269%20160%2022.619%20160H137.381C149.873%20160%20160%20149.873%20160%20137.381V22.619C160%2010.1269%20149.873%200%20137.381%200Z'%20fill='black'/%3e%3cpath%20d='M82.771%2033.208L75.0661%2044.157C74.4609%2045.0175%2073.6581%2045.7202%2072.7251%2046.2063C71.7922%2046.6924%2070.7562%2046.9476%2069.7043%2046.9506H27.7104V33.1629L82.771%2033.208Z'%20fill='white'/%3e%3cpath%20d='M135.083%2033.2075L68.9835%20126.837H24.917L91.0167%2033.2075H135.083Z'%20fill='white'/%3e%3cpath%20d='M77.2741%20126.837L85.024%20115.843C85.6315%20114.988%2086.4359%20114.292%2087.3692%20113.814C88.3024%20113.336%2089.3371%20113.089%2090.3859%20113.095H132.335V126.612L77.2741%20126.837Z'%20fill='white'/%3e%3c/g%3e%3cdefs%3e%3cclipPath%20id='clip0_3_10'%3e%3crect%20width='160'%20height='160'%20fill='white'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e) Z-AI | Z.AI: GLM 4.5 Air (free) z-ai/glm-4.5-air:free | 131K | FREE |
 Meta-Llama | Meta: Llama 3.2 3B Instruct (free) meta-llama/llama-3.2-3b-instruct:free | 131K | FREE |
| NVIDIA | NVIDIA: Nemotron Nano 9B V2 (free) nvidia/nemotron-nano-9b-v2:free | 128K | FREE |
| Mistral | Mistral: Mistral Small 3.1 24B (free) mistralai/mistral-small-3.1-24b-instruct:free | 128K | FREE |
| Meta-Llama | Meta: Llama 3.3 8B Instruct (free) meta-llama/llama-3.3-8b-instruct:free | 128K | FREE |
| Meta-Llama | Meta: Llama 4 Maverick (free) meta-llama/llama-4-maverick:free | 128K | FREE |
| Meta-Llama | Meta: Llama 4 Scout (free) meta-llama/llama-4-scout:free | 128K | FREE |
| Gemini | Google: Gemma 3 27B (free) google/gemma-3-27b-it:free | 96K | FREE |
agentica-org | Agentica: Deepcoder 14B Preview (free) agentica-org/deepcoder-14b-preview:free | 96K | FREE |
| Meta-Llama | Meta: Llama 3.3 70B Instruct (free) meta-llama/llama-3.3-70b-instruct:free | 66K | FREE |
| Meta-Llama | Meta: Llama 3.1 405B Instruct (free) meta-llama/llama-3.1-405b-instruct:free | 66K | FREE |
| DeepSeek | DeepSeek: DeepSeek V3.1 (free) deepseek/deepseek-chat-v3.1:free | 64K | FREE |
| DeepSeek | DeepSeek: R1 Distill Qwen 14B (free) deepseek/deepseek-r1-distill-qwen-14b:free | 64K | FREE |
| Qwen | Qwen: Qwen3 4B (free) qwen/qwen3-4b:free | 41K | FREE |
| Qwen | Qwen: Qwen3 30B A3B (free) qwen/qwen3-30b-a3b:free | 41K | FREE |
| Qwen | Qwen: Qwen3 8B (free) qwen/qwen3-8b:free | 41K | FREE |
| Qwen | Qwen: Qwen3 14B (free) qwen/qwen3-14b:free | 41K | FREE |
| Qwen | Qwen: QwQ 32B (free) qwen/qwq-32b:free | 33K | FREE |
| Qwen | Qwen: Qwen2.5 VL 72B Instruct (free) qwen/qwen2.5-vl-72b-instruct:free | 33K | FREE |
| Qwen | Qwen2.5 Coder 32B Instruct (free) qwen/qwen-2.5-coder-32b-instruct:free | 33K | FREE |
| Qwen | Qwen2.5 72B Instruct (free) qwen/qwen-2.5-72b-instruct:free | 33K | FREE |
| MoonshotAI | MoonshotAI: Kimi K2 0711 (free) moonshotai/kimi-k2:free | 33K | FREE |
| Gemini | Google: Gemma 3 4B (free) google/gemma-3-4b-it:free | 33K | FREE |
| Gemini | Google: Gemma 3 12B (free) google/gemma-3-12b-it:free | 33K | FREE |
| GPT | OpenAI: gpt-oss-120b (free) openai/gpt-oss-120b:free | 33K | FREE |
| Mistral | Mistral: Devstral Small 2505 (free) mistralai/devstral-small-2505:free | 33K | FREE |
| Mistral | Mistral: Mistral Small 3 (free) mistralai/mistral-small-24b-instruct-2501:free | 33K | FREE |
| Mistral | Mistral: Mistral 7B Instruct (free) mistralai/mistral-7b-instruct:free | 33K | FREE |
cognitivecomputations | Venice: Uncensored (free) cognitivecomputations/dolphin-mistral-24b-venice-edition:free | 33K | FREE |
cognitivecomputations | Dolphin3.0 R1 Mistral 24B (free) cognitivecomputations/dolphin3.0-r1-mistral-24b:free | 33K | FREE |
cognitivecomputations | Dolphin3.0 Mistral 24B (free) cognitivecomputations/dolphin3.0-mistral-24b:free | 33K | FREE |
Tencent | Tencent: Hunyuan A13B Instruct (free) tencent/hunyuan-a13b-instruct:free | 33K | FREE |
shisa-ai | Shisa AI: Shisa V2 Llama 3.3 70B (free) shisa-ai/shisa-v2-llama3.3-70b:free | 33K | FREE |
arliai | ArliAI: QwQ 32B RpR v1 (free) arliai/qwq-32b-arliai-rpr-v1:free | 33K | FREE |
rekaai | Reka: Flash 3 (free) rekaai/reka-flash-3:free | 33K | FREE |
| Qwen | Qwen: Qwen2.5 VL 32B Instruct (free) qwen/qwen2.5-vl-32b-instruct:free | 8K | FREE |
| Gemini | Google: Gemma 3n 2B (free) google/gemma-3n-e2b-it:free | 8K | FREE |
| Gemini | Google: Gemma 3n 4B (free) google/gemma-3n-e4b-it:free | 8K | FREE |
| Gemini | Google: Gemma 2 9B (free) google/gemma-2-9b-it:free | 8K | FREE |
| DeepSeek | DeepSeek: R1 Distill Llama 70B (free) deepseek/deepseek-r1-distill-llama-70b:free | 8K | FREE |
Important Information
• Free Tier Limitations: While these models have zero token costs, they may have rate limits, usage quotas, or require API keys from the respective providers.
• Availability: Free pricing may change at any time. Always verify current pricing with the provider before production use.
• Performance: Free models may have different performance characteristics compared to paid alternatives.
• Updates: This list is automatically updated every 12 hours from the OpenRouter API.