Cheapest LLM API
738 text models sorted by the lowest output price per 1M tokens across every provider, with their quality score beside it.
/
 SabaMistralPrompt cachingJSON+1 | $0.60/1Mvia OpenRouter | 33K | $0.20/1M | $0.60/1M | — | — | |
 Solar Pro3UpstagePrompt cachingJSON+2 | $0.60/1Mvia OpenRouter | 131K | $0.15/1M | $0.60/1M | — | — | |
 MiMo-V2.5-ProXiaomiMITPrompt caching+3 | $0.609/1Mvia OpenRouter | 1.05M | $0.304/1M | $0.609/1M | 1480 | 5K | |
| Kolibri 1Aleph Alpha | $0.616/1Mvia Cortecs | — | $0.168/1M | $0.616/1M | — | — | |
 WizardLM-2 8x22BMicrosoftReasoning | $0.62/1Mvia Hugging Face | 66K | $0.62/1M | $0.62/1M | — | — | |
| Ahm Phi 3.5 Moe InstructMicrosoftMIT | $0.64/1Mvia Azure | — | $0.16/1M | $0.64/1M | — | — | |
 Gemma 2 27BGoogleGemmaJSON | $0.65/1Mvia OpenRouter | 8K | $0.65/1M | $0.65/1M | 1231 | 14K | |
| Granite 4.2 30BIBMApache 2.0 | $0.65/1Mvia Hugging Face | — | $0.16/1M | $0.65/1M | 1361 | 2K | |
| UReMM SLERP 13BUndi95JSON | $0.65/1Mvia OpenRouter | 6K | $0.35/1M | $0.65/1M | — | — | |
 Doubao Seed 1.6 LiteByteDancePrompt cachingJSON+3 | $0.656/1Mvia AIHubMix | 256K | $0.082/1M | $0.656/1M | — | — | |
 Qwen3.5 PlusAlibabaJSONReasoning+2 | $0.658/1Mvia AIHubMix | 1M | $0.115/1M | $0.688/1M | — | — | |
| Qwen3.5 27BAlibabaApache 2.0JSON+3 | $0.677/1Mvia AIHubMix | 262K | $0.30/1M | $2.40/1M | 1409 | 2K | |
| Ahm Phi 3 Medium 128KMicrosoftMIT | $0.68/1Mvia Azure | — | $0.17/1M | $0.68/1M | — | — | |
| Phi-3-medium-4k-instructMicrosoftMIT | $0.68/1Mvia Azure | — | $0.17/1M | $0.68/1M | 1138 | — | |
| Qwen3.5 PlusAlibabaJSON | $0.688/1Mvia EmpirioLabs AI | 1M | $0.115/1M | $0.688/1M | — | — | |
| Qwen3-VL-8B-ThinkingAlibabaApache 2.0JSON+3 | $0.694/1Mvia SiliconFlow | 131K | $0.069/1M | $0.694/1M | — | 6K | |
| MiMo-V2.6-ProXiaomiPrompt cachingJSON+3 | $0.696/1Mvia CometAPI | 1.05M | $0.348/1M | $0.696/1M | 1625 | 72K | |
| Hermes 3 70B InstructNous ResearchLlama 3JSON | $0.70/1Mvia Hugging Face | 131K | $0.70/1M | $0.70/1M | — | — | |
| Jamba InstructAI21 Labs | $0.70/1Mvia Amazon Bedrock | — | $0.50/1M | $0.70/1M | — | 35K | |
| LFM2.5-24B-A2BLiquid AIOpen weights · with termsPrompt caching+3 | $0.70/1Mvia OpenRouter | 128K | $0.05/1M | $0.70/1M | — | 6K | |
 Llama 3 70B InstructMeta | $0.70/1Mvia AIHubMix | — | $0.70/1M | $0.70/1M | 1221 | 24K | |
| Longcat-Flash-ChatMeituanMIT | $0.70/1Mvia AIHubMix | — | $0.14/1M | $0.70/1M | 1423 | — | |
| Mixtral 8x7b InstructMistral | $0.70/1Mvia Amazon Bedrock | — | $0.45/1M | $0.70/1M | — | — | |
| Qwen2-VL-7B-InstructAlibabaApache 2.0Vision | $0.70/1Mvia AIHubMix | — | $0.28/1M | $0.70/1M | 990 | — | |
| Llama3.2 90B InstructMeta | $0.72/1Mvia Amazon Bedrock | — | $0.72/1M | $0.72/1M | — | — | |
 Toast 1MixedbreadPrompt cachingJSON+1 | $0.72/1Mvia Vercel AI Gateway | 131K | $0.30/1M | $0.72/1M | — | — | |
| Mercury 2InceptionPrompt cachingJSON+2 | $0.75/1Mvia OpenRouter | 128K | $0.25/1M | $0.75/1M | 1355 | 3K | |
| Mercury 2.5 PreviewInceptionPrompt cachingReasoning+1 | $0.75/1Mvia AIHubMix | 260K | $0.20/1M | $0.75/1M | — | — | |
| Qwen MT PlusAlibaba | $0.75/1Mvia Jiekou.AI | 16K | $0.259/1M | $0.775/1M | — | — | |
 Weaver (alpha)MancerJSON | $0.75/1Mvia OpenRouter | 8K | $0.40/1M | $0.75/1M | — | — | |
| Mixtral 8x7B Instruct v0.1 (Deep Infra)MistralApache 2.0 | $0.761/1Mvia Cortecs | — | $0.49/1M | $0.761/1M | 1132 | — | |
| SLlama 3.3 70B EuryaleSao10K | $0.793/1Mvia AI/ML API | — | $0.688/1M | $0.793/1M | — | — | |
 DeepSeek-V3.1DeepSeekMITPrompt caching+3 | $0.798/1Mvia Poe | 164K | $0.212/1M | $0.798/1M | 1420 | — | |
 Arcee Trinity Large Thinking (Public Preview)Arcee AIOpen weights · permissivePrompt caching+2 | $0.80/1Mvia OpenRouter | 262K | $0.25/1M | $0.80/1M | — | — | |
| Muse Glimmer 30BMetaPrompt cachingJSON+3 | $0.80/1Mvia EmpirioLabs AI | 131K | $0.20/1M | $0.80/1M | — | — | |
| Qwen2-72B-InstructAlibabaOpen weights · with terms | $0.80/1Mvia AIHubMix | — | $0.80/1M | $0.80/1M | 1203 | — | |
| Qwen2.5 3B InstructAlibabaNon-commercial | $0.80/1Mvia AIHubMix | — | $0.40/1M | $0.80/1M | — | 2K | |
| TSkyfall 36B V2ThedrummerOpen weightsPrompt caching+1 | $0.80/1Mvia OpenRouter | 33K | $0.55/1M | $0.80/1M | — | — | |
 GLM-4.5VZhipu AIMITPrompt caching+4 | $0.822/1Mvia AIHubMix | 66K | $0.60/1M | $1.80/1M | 1333 | — | |
| DeepSeek V3 0324DeepSeekMITTool calling | $0.822/1Mvia APIMart | 128K | $0.206/1M | $0.822/1M | — | — | |
| Qwen3.6 FlashAlibabaJSONReasoning+2 | $0.823/1Mvia APIMart | 1M | $0.165/1M | $0.99/1M | — | — | |
| SL31 70B Euryale V2.2Sao10KCC BY-NC 4.0 | $0.85/1Mvia Deep Infra | 16K | $0.85/1M | $0.85/1M | — | — | |
| SLlama 3.1 Euryale 70B v2.2Sao10KJSON | $0.85/1Mvia OpenRouter | 131K | $0.85/1M | $0.85/1M | — | — | |
 MiniMax M2.1MiniMaxOpen weights · with termsPrompt caching+3 | $0.864/1Mvia APIMart | 205K | $0.216/1M | $0.864/1M | — | 1K | |
| Qwen3 VL 235B A22B InstructAlibabaApache 2.0Prompt caching+3 | $0.88/1Mvia Deep Infra | 262K | $0.20/1M | $0.88/1M | — | — | |
| Qwen3 VL InstructAlibabaPrompt cachingTool calling+1 | $0.88/1Mvia Vercel AI Gateway | 262K | $0.20/1M | $0.88/1M | — | 15K | |
| DeepSeek V3DeepSeekOpen weightsReasoning+1 | $0.89/1Mvia Deep Infra | 64K | $0.32/1M | $0.89/1M | — | 9K | |
| Codestral (latest)MistralPrompt cachingJSON+1 | $0.90/1Mvia Vercel AI Gateway | 128K | $0.30/1M | $0.90/1M | — | 720 | |
| Codestral 25.08MistralPrompt cachingJSON+1 | $0.90/1Mvia DevPass (LLM Gateway) | 131K | $0.30/1M | $0.90/1M | — | — | |
| MiniMax-M3MiniMaxOpen weights · with termsPrompt caching+4 | $0.90/1Mvia EmpirioLabs AI | 1M | $0.30/1M | $1.20/1M | 1482 | 26K |
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