Cheapest LLM API
738 text models sorted by the lowest output price per 1M tokens across every provider, with their quality score beside it.
/
 DeepSeek V4 FlashDeepSeekMITPrompt caching+3 | $0.17/1Mvia Opper | 1.05M | $0.07/1M | $0.17/1M | — | 51K | |
 Qwen2.5-32B-InstructAlibabaApache 2.0 | $0.175/1Mvia SiliconFlow | — | $0.175/1M | $0.175/1M | — | — | |
 NVIDIA-Nemotron-Nano-9B-v2NVIDIAOpen weights · with terms | $0.176/1Mvia AIHubMix | — | $0.044/1M | $0.176/1M | — | — | |
 Hy-MT2-1.8BTencentApache 2.0 | $0.177/1Mvia OpenRouter | 8K | $0.044/1M | $0.177/1M | — | — | |
| Tencent Hy-MT2-LiteTencent | $0.177/1Mvia Vercel AI Gateway | 8K | $0.044/1M | $0.177/1M | — | — | |
 Laguna S 2.1PoolsideReasoningTool calling | $0.18/1Mvia OpenRouter | 262K | $0.09/1M | $0.18/1M | — | 3K | |
 Ling 3.0 Flash FinInclusionaiMITPrompt caching+1 | $0.18/1Mvia Hugging Face | 256K | $0.06/1M | $0.18/1M | — | — | |
| Ling 3.0 Flash VLInclusionaiMITPrompt caching+4 | $0.18/1Mvia Deep Infra | 131K | $0.06/1M | $0.18/1M | — | — | |
 Mistral-7B-Instruct-v0.1MistralApache 2.0 | $0.19/1Mvia Cloudflare Workers AI | — | $0.11/1M | $0.19/1M | — | — | |
 Apertus 8B InstructSwiss Ai | $0.20/1Mvia Hugging Face | — | $0.10/1M | $0.20/1M | — | — | |
| DeepSeek R1 Distill Qwen 32BDeepSeekMIT | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | 2K | |
| DeepSeek V4 Flash 0424DeepSeekReasoningTool calling | $0.20/1Mvia Requesty | 1.05M | $0.10/1M | $0.20/1M | — | — | |
 Gemma 3 1B ItGoogleGemma | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | 3K | |
| Gemma 3n E4B ItGoogleGemma | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | — | |
 GLM-5.3-FlashZhipu AIMITPrompt caching+4 | $0.20/1Mvia APIMart | 1.05M | $0.15/1M | $0.50/1M | 1608 | 121K | |
| Hunyuan Mt 7BTencentOpen weights | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | — | |
 Llama 3.2 11B Vision InstructMetaLlama 3.2 | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | 966 | — | |
| Llama 4 MaverickMetaJSONTool calling+1 | $0.20/1Mvia AIHubMix | 1.05M | $0.20/1M | $0.20/1M | — | 9K | |
| Llama 4 Scout 17B InstructMetaJSONTool calling+1 | $0.20/1Mvia AIHubMix | 1.31M | $0.20/1M | $0.20/1M | — | 7K | |
| Ministral 14BMistralPrompt cachingJSON+2 | $0.20/1Mvia DevPass (LLM Gateway) | 262K | $0.20/1M | $0.20/1M | — | — | |
| Ministral 14B (Arkanecloud)MistralPrompt cachingJSON+2 | $0.20/1Mvia Vercel AI Gateway | 262K | $0.20/1M | $0.20/1M | — | 270 | |
| Ministral 3 14BMistralApache 2.0 | $0.20/1Mvia Amazon Bedrock | — | $0.20/1M | $0.20/1M | — | — | |
| Ministral 3 14B 2512Mistral | $0.20/1Mvia Mistral | 262K | $0.20/1M | $0.20/1M | — | 1K | |
| Mistral Small 3.2 24BMistralPrompt cachingJSON+2 | $0.20/1Mvia Deep Infra | 256K | $0.075/1M | $0.20/1M | — | — | |
| Nemotron 3 Nano 30B A3BNVIDIAJSONReasoning+1 | $0.20/1Mvia Novita AI | 262K | $0.05/1M | $0.20/1M | — | 390 | |
| Nemotron Lightning 3.5 30B A3BNVIDIAPrompt cachingJSON+2 | $0.20/1Mvia Requesty | 262K | $0.05/1M | $0.20/1M | — | 860 | |
| Qwen FlashAlibabaPrompt cachingJSON+1 | $0.20/1Mvia AIHubMix | 1M | $0.022/1M | $0.216/1M | — | — | |
| Qwen2-1.5B-InstructAlibabaApache 2.0 | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | 37K | |
| Qwen2.5 Math 1.5b InstructAlibabaApache 2.0 | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | — | |
| Qwen3 14BAlibabaApache 2.0JSON+2 | $0.20/1Mvia Hugging Face | 41K | $0.07/1M | $0.20/1M | — | 3K | |
| Reka Flash 3Reka AIJSONReasoning | $0.20/1Mvia OpenRouter | 66K | $0.10/1M | $0.20/1M | — | — | |
 Solar Mini 4UpstagePrompt cachingJSON+2 | $0.20/1Mvia OpenRouter | 524K | $0.05/1M | $0.20/1M | — | 6K | |
 UI-TARS 7BByteDanceApache 2.0Prompt caching+2 | $0.20/1Mvia OpenRouter | 128K | $0.10/1M | $0.20/1M | — | — | |
| GLM-4.6V-FlashZhipu AIMITPrompt caching+2 | $0.218/1Mvia ZenMux | 200K | $0.022/1M | $0.218/1M | — | — | |
| Ling 3.0 Flash SanteInclusionaiMITPrompt caching+2 | $0.22/1Mvia Novita AI | 262K | $0.075/1M | $0.22/1M | — | — | |
| Mistral 7B Instruct V0.2MistralApache 2.0 | $0.221/1Mvia Cortecs | — | $0.16/1M | $0.221/1M | 1090 | — | |
 MiMo-V2.5XiaomiMITPrompt caching+4 | $0.224/1Mvia CometAPI | 1.05M | $0.112/1M | $0.224/1M | 1438 | 10K | |
| Gemma 4 26B A4B ITGoogleApache 2.0Prompt caching+4 | $0.225/1Mvia OpenRouter | 262K | $0.15/1M | $0.60/1M | — | 3K | |
| Ling 3.1 FlashInclusionaiMITPrompt caching+2 | $0.225/1Mvia Deep Infra | 262K | $0.075/1M | $0.225/1M | — | 38K | |
| NVIDIA Nemotron Nano 9B v2NVIDIAOpen weights · with termsReasoning+1 | $0.23/1Mvia Vercel AI Gateway | 131K | $0.06/1M | $0.23/1M | — | — | |
| Qwen PlusAlibabaPrompt cachingJSON+1 | $0.23/1Mvia CrazyRouter | 1M | $0.115/1M | $0.287/1M | 1326 | — | |
| Schematron V2 SmallInference NetPrompt cachingJSON | $0.23/1Mvia OpenRouter | 128K | $0.05/1M | $0.23/1M | — | — | |
| Nemotron 3 Nano Omni 30B TEENVIDIAJSONReasoning+1 | $0.24/1Mvia Requesty | 300K | $0.06/1M | $0.24/1M | — | 780 | |
 Nova Lite (EU)AmazonPrompt cachingJSON+2 | $0.24/1Mvia Vercel AI Gateway | 300K | $0.06/1M | $0.24/1M | — | — | |
| Nova Lite 1.0AmazonTool callingVision | $0.24/1Mvia OpenRouter | 300K | $0.06/1M | $0.24/1M | — | — | |
| Qwen 2.5 VL 32B InstructAlibabaApache 2.0JSON+2 | $0.24/1Mvia AIHubMix | — | $0.24/1M | $0.24/1M | 1152 | — | |
| Qwen2 57B A14B InstructAlibabaApache 2.0 | $0.24/1Mvia AIHubMix | — | $0.24/1M | $0.24/1M | — | 4K | |
| Us Gov.nvidia.nemotron Nano 3 30BNVIDIA | $0.24/1Mvia Amazon Bedrock | — | $0.06/1M | $0.24/1M | — | — | |
 Qianfan OcrBaiduApache 2.0Vision | $0.248/1Mvia AIHubMix | 32K | $0.062/1M | $0.248/1M | — | — | |
| Granite 3.0 8B InstructIBMApache 2.0 | $0.25/1Mvia Replicate | — | $0.05/1M | $0.25/1M | — | — |
Frequently asked questions
The first rows of this list, by lowest output price. The cheapest models are usually small or older; check the score column and the chart below for the best quality at a given price.
Yes: several providers offer free, rate-limited tiers. They are listed on the free AI models page; this page counts paid prices only.
The labelled points in the chart: each one has the best LMArena score among models at its price or less. Pick the cheapest of them that is good enough for your task.
Can't find what you're looking for? Contact us