Free AI models
110 models with a free way in: a free API tier, or free rate-limited hosting.
/
 GLM-5.3Zhipu AIOpen weights · with termsPrompt caching+3 | $1.10/1Mvia NanoGPT | 1.05M | $1.40/1M | $4.40/1M | 276K | Aug 25 | |
 DeepSeek V4.1 FlashDeepSeekMITPrompt caching+4 | $0.03/1Mvia UnoRouter | 1.05M | $0.007/1M | $0.03/1M | 138K | Sep 10 | |
| GLM-5.3-FlashZhipu AIMITPrompt caching+4 | $0.20/1Mvia APIMart | 1.05M | $0.15/1M | $0.50/1M | 121K | Aug 25 | |
 Gemini 3.8 FlashGooglePrompt cachingJSON+3 | $3/1Mvia APIMart | 1.05M | $0.75/1M | $3.75/1M | 102K | Sep 2 | |
 MiniMax-M3.1-FlashMiniMaxOpen weights · with termsPrompt caching+4 | $0.45/1Mvia EmpirioLabs AI | 1.05M | $0.15/1M | $0.60/1M | 29K | Oct 17 | |
 MiMo-V2.6-FlashXiaomiPrompt cachingJSON+3 | $0.10/1Mvia UnoRouter | 1.05M | $0.05/1M | $0.10/1M | 28K | Sep 21 | |
| LongCat 2.5 PreviewMeituanPrompt cachingJSON+3 | $1.18/1Mvia ZenMux | 1.05M | $0.30/1M | $1.18/1M | 19K | Sep 26 | |
 Nemotron 3.5 Super VL (free)NVIDIAVision | Free/1Mvia Kenari | — | Free/1M | Free/1M | 18K | — | |
| Gemini 2.5 ProGooglePrompt cachingJSON+3 | $8/1Mvia APIMart | 1.05M | $1.25/1M | $10/1M | 14K | Mar 20, 2025 | |
| GPT OSS 20BOpenAIApache 2.0JSON+2 | $0.09/1Mvia OpenRouter | 131K | $0.018/1M | $0.09/1M | 12K | Aug 4, 2025 | |
| Gemini 2.5 FlashGooglePrompt cachingJSON+3 | $2/1Mvia APIMart | 1.05M | — | $2.50/1M | 11K | Mar 20, 2025 | |
| Kimi K2.6Moonshot AIOpen weights · with termsPrompt caching+4 | $2.40/1Mvia APIYI | 262K | $0.903/1M | $3.75/1M | 11K | Apr 14 | |
| GLM-4.7-FlashZhipu AIMITJSON+2 | $0.40/1Mvia Amazon Bedrock | 200K | $0.07/1M | $0.40/1M | 7K | Jan 19 | |
| Gemma 4GoogleApache 2.0JSON+3 | $0.30/1Mvia FastRouter | 262K | $0.10/1M | $0.30/1M | 6K | Mar 11 | |
| Nemotron 3.5 Lightning 30B A3BNVIDIAReasoningTool calling | $0.16/1Mvia Deep Infra | 1M | Free/1M | Free/1M | 5K | Aug 11 | |
| Gemma 3 4B ITGoogleGemmaPrompt caching+2 | $0.05/1Mvia OpenRouter | 131K | $0.04/1M | $0.05/1M | 4K | Feb 20, 2025 | |
| Gemma 4 26B A4B ITGoogleApache 2.0Prompt caching+4 | $0.225/1Mvia OpenRouter | 262K | $0.15/1M | $0.60/1M | 3K | Mar 11 | |
| Nemotron 3.5 Bolt E4BNVIDIA | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 2K | — | |
| Gemma 3 12B ITGoogleGemmaJSON+2 | $0.10/1Mvia Helicone | 131K | $0.05/1M | $0.10/1M | 2K | Mar 1, 2025 | |
| Nemotron 3 Super 120B A12BNVIDIAJSONReasoning+1 | $0.40/1Mvia Deep Infra | 262K | Free/1M | Free/1M | 2K | Mar 11 | |
| Gemma 2BGoogleGemma | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 1K | Feb 8, 2024 | |
| Nemotron 3 Ultra 550B A55BNVIDIAReasoningTool calling | $2.20/1Mvia Deep Infra | 1M | Free/1M | Free/1M | 1K | Jun 4 | |
| Nemotron-4-340B-InstructNVIDIAOpen weights · with terms | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 760 | Jun 13, 2024 | |
| Nemotron 3 Nano OmniNVIDIAOpen weights · with termsReasoning+2 | Free/1Mvia Kenari | 256K | Free/1M | Free/1M | 670 | Apr 24 | |
| Nemotron Parse 2.0NVIDIA | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 640 | — | |
| Nemotron 3 Nano 30B A3BNVIDIAJSONReasoning+1 | $0.20/1Mvia Novita AI | 262K | $0.05/1M | $0.20/1M | 390 | Dec 15, 2025 | |
 Codestral 22B Instruct V0.1Mistral | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 180 | — | |
 Ahm Phi 3.5 Moe InstructMicrosoftMIT | $0.64/1Mvia Azure | — | $0.16/1M | $0.64/1M | — | Aug 17, 2024 | |
 Beam 1.0 501B A23BReflectionPrompt cachingJSON+2 | $1/1Mvia OpenRouter | 1.05M | $0.25/1M | $1/1M | — | Oct 16 | |
| Codegemma 1.1 7BGoogle | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | — | |
| Codegemma 7BGoogleGemma | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Mar 21, 2024 | |
 Codellama 70BMeta | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | — | |
| Cosmos Reason2 8BNVIDIAOpen weights · with terms | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Dec 12, 2025 | |
| DeepSeek Coder 6.7B InstructDeepSeekOpen weights · with terms | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Oct 29, 2023 | |
| DeplotGoogleApache 2.0 | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Apr 3, 2023 | |
| DiffusionGemmaGoogleApache 2.0 | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Jun 9 | |
| RFlint 40B FreeRecursiveJSONReasoning+1 | Free/1Mvia OpenCode | 262K | Free/1M | Free/1M | — | Oct 21 | |
| Gemini 2.5 Flash-LiteGooglePrompt cachingJSON+3 | $0.32/1Mvia APIMart | 1.05M | — | $0.40/1M | — | Jun 17, 2025 | |
| Gemini 3 Flash PreviewGooglePrompt cachingJSON+3 | $1.50/1Mvia Vertex | 1.05M | — | $3/1M | — | Dec 17, 2025 | |
| Ai Synthetic Video DetectorNVIDIA | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | — | |
| Gemini 3.8 Flash TTSGoogle | $6.30/1Mvia Kie.ai | 8K | — | $9/1M | 137K | Sep 23 | |
| Gemini 3.8 LiveGoogleTool calling | $4.50/1Mvia Vercel AI Gateway | 131K | $0.75/1M | $4.50/1M | 38K | Sep 15 | |
| Gemini 3.1 Flash TTS PreviewGoogleReasoning | $14/1Mvia Kie.ai | 8K | — | $20/1M | 10K | Apr 24 | |
| Gemini 3.8 Flash-Lite TTSGoogle | $4.20/1Mvia Kie.ai | 8K | — | $6/1M | 8K | Sep 23 | |
| Gemini 2.5 Flash Native Audio Preview 09-2025Google | $2/1Mvia Google | 131K | $0.50/1M | $2/1M | — | — | |
| Gemini 2.5 Flash TTSGoogle | $10/1Mvia Google | 8K | — | $10/1M | — | Oct 8 | |
| Nemotron 3.5 Embed 1BNVIDIAOpen weights · permissive | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 4K | Oct 7 | |
| Nemotron 3 Embed 1BNVIDIAOpen weights · permissive | Free/1Mvia Nvidia | — | Free/1M | Free/1M | 390 | Jul 14 | |
| Embed Qa 4NVIDIA | Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | — | |
| Nemotron 3.5 Content SafetyNVIDIAOpen weights · permissiveReasoning+1 | $0.20/1Mvia OpenRouter | 131K | Free/1M | Free/1M | 250 | May 22 |
Frequently asked questions
They have a free tier, not unlimited use: expect rate limits, daily caps or lower priority. Check the provider's terms before you build on one.
The list is ranked by quality. Free tiers usually cover smaller or older versions, so compare the free model with its paid sibling before choosing.
Sign up with a provider that has a free tier, such as Google AI Studio for Gemini, or an aggregator that offers free model variants.
Can't find what you're looking for? Contact us