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 R1 Distill Qwen 14BDeepSeekMIT | $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | — | |
 Doubao 1.5 Lite 32KByteDance | $0.10/1Mvia AIHubMix | — | $0.05/1M | $0.10/1M | — | 480 | |
| Doubao Seed 2.0 Mini 260428ByteDanceJSONReasoning+2 | $0.10/1Mvia Fal | 256K | $0.10/1M | $0.40/1M | — | — | |
 Gemma 3 12B ITGoogleGemmaJSON+2 | $0.10/1Mvia Helicone | 131K | $0.05/1M | $0.10/1M | 1334 | 2K | |
| Gemma 7B ItGoogleGemma | $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | 1056 | — | |
 GLM 4 FlashZhipu AI | $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | 2K | |
| GLM-4 32B (0414-128k)Zhipu AI | $0.10/1Mvia DevPass (LLM Gateway) | — | $0.10/1M | $0.10/1M | — | — | |
 Llama 2 7BMetaLlama 2 | $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | 1053 | — | |
| Llama 3.2 1B InstructMetaLlama 3.2 | $0.10/1Mvia Amazon Bedrock | 60K | $0.10/1M | $0.10/1M | — | — | |
 MiMo-V2.6-FlashXiaomiPrompt cachingJSON+3 | $0.10/1Mvia UnoRouter | 1.05M | $0.05/1M | $0.10/1M | 1634 | 28K | |
 Ministral 3 3B 2512Mistral | $0.10/1Mvia Mistral | 262K | $0.10/1M | $0.10/1M | — | 3K | |
| Ministral 3BMistralPrompt cachingJSON+2 | $0.10/1Mvia DevPass (LLM Gateway) | 131K | $0.10/1M | $0.10/1M | — | 2K | |
 Nex-N2.5-MiniNex AgiPrompt cachingJSON+2 | $0.10/1Mvia OpenRouter | 262K | $0.025/1M | $0.10/1M | — | — | |
 Qwen3 235B A22B Instruct 2507AlibabaApache 2.0JSON+1 | $0.10/1Mvia Requesty | 262K | $0.071/1M | $0.10/1M | — | — | |
| Qwen3.5 2BAlibabaApache 2.0JSON+3 | $0.10/1Mvia Requesty | 262K | $0.02/1M | $0.10/1M | — | 3K | |
| Reka EdgeReka AIJSONTool calling+1 | $0.10/1Mvia OpenRouter | 16K | $0.10/1M | $0.10/1M | — | — | |
| ThudmZhipu AIMIT | $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | — | |
| Qwen3.7 FlashAlibabaJSON | $0.11/1Mvia EmpirioLabs AI | 1M | $0.028/1M | $0.11/1M | — | 5K | |
| Granite 4.0 H MicroIBMApache 2.0JSON | $0.112/1Mvia Cloudflare Workers AI | 131K | $0.017/1M | $0.112/1M | — | — | |
 Aihubmix Phi 4 Mini (reasoning)MicrosoftMIT | $0.12/1Mvia AIHubMix | 128K | $0.12/1M | $0.12/1M | — | — | |
| Doubao Lite 32KByteDance | $0.12/1Mvia AIHubMix | — | $0.06/1M | $0.12/1M | — | — | |
| Doubao Lite 4KByteDance | $0.12/1Mvia AIHubMix | — | $0.06/1M | $0.12/1M | — | — | |
| Granite 4.2 3BIBMApache 2.0 | $0.12/1Mvia Hugging Face | — | $0.03/1M | $0.12/1M | 1294 | — | |
 Laguna XS 2.1PoolsideReasoningTool calling | $0.12/1Mvia OpenRouter | 262K | $0.06/1M | $0.12/1M | — | — | |
 Solar Pro 4UpstagePrompt cachingJSON+2 | $0.127/1Mvia AI/ML API | 524K | $0.032/1M | $0.127/1M | — | 11K | |
| DeepSeek R1 Distill Llama 70BDeepSeekMITReasoning | $0.13/1Mvia Helicone | 32K | $0.03/1M | $0.13/1M | — | — | |
| Qwen3.5 9BAlibabaApache 2.0Prompt caching+4 | $0.13/1Mvia EmpirioLabs AI | 262K | $0.09/1M | $0.13/1M | — | 19K | |
| DeepSeek V4 Flash 0731DeepSeekMITPrompt caching+3 | $0.133/1Mvia OpenRouter | 1.05M | $0.044/1M | $0.133/1M | — | 4K | |
| AutoGLM Phone 9B MultilingualZhipu AIMIT | $0.138/1Mvia Hugging Face | — | $0.035/1M | $0.138/1M | — | — | |
| GPT OSS 120BOpenAIApache 2.0Prompt caching+3 | $0.14/1Mvia Requesty | 131K | $0.032/1M | $0.14/1M | 1366 | 35K | |
| Hermes 2 Pro Llama 3 8BNous ResearchLlama 3 | $0.14/1Mvia Helicone | — | $0.14/1M | $0.14/1M | — | — | |
 Nova Micro (APAC)AmazonPrompt cachingJSON+1 | $0.14/1Mvia Amazon Bedrock | 128K | $0.035/1M | $0.14/1M | — | — | |
| Nova Micro 1.0AmazonTool calling | $0.14/1Mvia OpenRouter | 128K | $0.035/1M | $0.14/1M | — | — | |
| Phi 4MicrosoftMITJSON | $0.14/1Mvia Deep Infra | 16K | $0.07/1M | $0.14/1M | 1217 | — | |
| Ministral 8BMistralPrompt cachingJSON+2 | $0.143/1Mvia AI/ML API | 262K | $0.143/1M | $0.143/1M | 1191 | 340 | |
| Qwen Doc TurboAlibaba | $0.144/1Mvia Alibaba | — | $0.087/1M | $0.144/1M | — | — | |
| Tongyi Intent Detect V3Alibaba | $0.144/1Mvia Alibaba | — | $0.058/1M | $0.144/1M | — | — | |
 Command R7BCohereCC BY-NC 4.0JSON | $0.15/1Mvia OpenRouter | 128K | $0.037/1M | $0.15/1M | — | — | |
| Mercury 2.5InceptionPrompt cachingJSON+2 | $0.15/1Mvia OpenRouter | 260K | $0.04/1M | $0.15/1M | — | 12K | |
| Ministral 3 8B 2512Mistral | $0.15/1Mvia Mistral | 262K | $0.15/1M | $0.15/1M | — | 1K | |
 Rnj-1 InstructEssentialai | $0.15/1Mvia Together AI | — | $0.15/1M | $0.15/1M | — | — | |
| Schematron V2 TurboInference NetPrompt cachingJSON | $0.15/1Mvia OpenRouter | 128K | $0.03/1M | $0.15/1M | — | — | |
| DeepSeek Llm 67B ChatDeepSeekOpen weights · with terms | $0.16/1Mvia AIHubMix | — | $0.16/1M | $0.16/1M | — | — | |
| DeepSeek Vl2DeepSeekOpen weights · with terms | $0.16/1Mvia AIHubMix | — | $0.16/1M | $0.16/1M | — | — | |
| Gemma 3 27BGoogleGemmaJSON+2 | $0.16/1Mvia Deep Infra | 131K | $0.08/1M | $0.16/1M | 1358 | 3K | |
| Llama 3.2 11B InstructMeta | $0.16/1Mvia Amazon Bedrock | — | $0.16/1M | $0.16/1M | — | 7K | |
 Nemotron 3.5 Lightning 30B A3BNVIDIAReasoningTool calling | $0.16/1Mvia Deep Infra | 1M | Free/1M | Free/1M | — | 5K | |
| Qwen2.5-Coder-32B-InstructAlibabaApache 2.0JSON | $0.16/1Mvia AIHubMix | 33K | $0.16/1M | $0.16/1M | 1230 | — | |
| QwQ-32B-PreviewAlibabaApache 2.0 | $0.16/1Mvia AIHubMix | — | $0.16/1M | $0.16/1M | 1162 | — | |
 Sarvam-105BSarvam AIReasoningTool calling | $0.16/1Mvia FastRouter | 128K | $0.04/1M | $0.16/1M | — | — |
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