Cheapest LLM API
738 text models sorted by the lowest output price per 1M tokens across every provider, with their quality score beside it.
/
| Claude Instant 1.2Anthropic | $3.96/1Mvia AIHubMix | — | $0.88/1M | $3.96/1M | — | — | |
| Claude Haiku 4.5 (latest)AnthropicPrompt cachingJSON+3 | $4/1Mvia APIMart | 200K | $1/1M | $5/1M | — | — | |
| Claude-Haiku-3.5Anthropic | $4/1Mvia Helicone | — | $0.80/1M | $4/1M | 1255 | 15K | |
 Llama 3.1 405B (reasoning)Meta | $4/1Mvia AIHubMix | — | $4/1M | $4/1M | — | 6K | |
| Moonshot V1 32KMoonshot AI | $4/1Mvia AIHubMix | — | $4/1M | $4/1M | — | — | |
| Moonshot V1 32K Vision PreviewMoonshot AI | $4/1Mvia AIHubMix | — | $4/1M | $4/1M | — | — | |
 Sakana NamazuSakana AIPrompt cachingJSON+3 | $4/1Mvia OpenRouter | 262K | $0.95/1M | $4/1M | — | — | |
 Qwen3.8 2.4T A95BAlibabaOpen weights · with termsPrompt caching+3 | $4.11/1Mvia APIMart | 1M | $2/1M | $6/1M | — | 234K | |
| Qwen3.8 MaxAlibabaPrompt cachingJSON+3 | $4.11/1Mvia APIMart | 1M | $1.65/1M | $4.95/1M | 1673 | 25K | |
| Qwen3.8 Max 0902AlibabaPrompt cachingJSON+3 | $4.11/1Mvia APIMart | 1M | $2/1M | $6/1M | — | 3K | |
| Muse Spark 1.1MetaPrompt cachingJSON+3 | $4.25/1Mvia EmpirioLabs AI | 1.05M | $1.25/1M | $4.25/1M | 1543 | — | |
| Muse Spark 1.2MetaPrompt cachingJSON+3 | $4.25/1Mvia EmpirioLabs AI | 1.05M | $1.25/1M | $4.25/1M | 1534 | — | |
| Muse Spark 1.3MetaPrompt cachingJSON+3 | $4.25/1Mvia EmpirioLabs AI | 1.05M | $1.25/1M | $4.25/1M | 1657 | 121K | |
| Muse Spark OpenMetaPrompt cachingJSON+3 | $4.25/1Mvia Baseten | 1.05M | $1.25/1M | $4.25/1M | 1527 | 74K | |
 GLM-5.2Zhipu AIPrompt cachingJSON | $4.40/1Mvia EmpirioLabs AI | 1M | $1.40/1M | $4.40/1M | — | — | |
| GLM-4.5 AirXZhipu AIPrompt caching | $4.50/1Mvia DevPass (LLM Gateway) | — | $1.10/1M | $4.50/1M | — | — | |
 DeepSeek V4 ProDeepSeekPrompt cachingJSON | $4.80/1Mvia EmpirioLabs AI | 1M | $2.40/1M | $4.80/1M | — | — | |
| DeepSeek V4 ProDeepSeekPrompt cachingJSON | $4.80/1Mvia EmpirioLabs AI | 1M | $2.40/1M | $4.80/1M | — | — | |
| Grok 4.6xAIPrompt cachingJSON+2 | $4.80/1Mvia APIMart | 500K | $2/1M | $6/1M | 1617 | 19K | |
| Grok 4.7xAIPrompt cachingJSON+2 | $4.80/1Mvia APIMart | 500K | $2/1M | $6/1M | 1637 | 221K | |
| Kimi K2 Turbo PreviewMoonshot AIPrompt cachingJSON+1 | $4.80/1Mvia AIHubMix | 262K | $1.20/1M | $4.80/1M | — | — | |
| Qwen3.7 MaxAlibabaPrompt cachingJSON | $4.95/1Mvia EmpirioLabs AI | 1M | $1.65/1M | $4.95/1M | — | — | |
| Qwen3.8 MaxAlibabaPrompt cachingJSON | $4.95/1Mvia EmpirioLabs AI | 1M | $1.65/1M | $4.95/1M | — | — | |
| Claude 4.5 HaikuAnthropic | $5/1Mvia Replicate | — | $1/1M | $5/1M | — | — | |
 Gemini 2.5 ProGooglePrompt cachingJSON+2 | $5/1Mvia AIHubMix | — | $1.25/1M | $5/1M | — | — | |
| Gemini Exp 1114Google | $5/1Mvia AIHubMix | — | $1.25/1M | $5/1M | — | — | |
| Gemini Robotics Er 2 Streaming PreviewGoogle | $5/1Mvia Google | — | — | $5/1M | — | — | |
| Gemini Robotics-ER 1.6 PreviewGoogleJSONReasoning+2 | $5/1Mvia OrcaRouter | — | $1/1M | $5/1M | — | — | |
| Gemini Robotics-ER 2 PreviewGoogle | $5/1Mvia Google | — | — | $5/1M | — | — | |
| Learnlm 1.5 Pro ExperimentalGoogle | $5/1Mvia AIHubMix | — | $1.25/1M | $5/1M | — | — | |
| AMagnum v4 72BAnthracite OrgJSON | $5/1Mvia OpenRouter | 33K | $2.50/1M | $5/1M | — | — | |
 Sonar ReasoningPerplexity | $5/1Mvia Helicone | — | $1/1M | $5/1M | — | — | |
 Aion 3.5Aion LabsPrompt cachingJSON+2 | $6/1Mvia OpenRouter | 262K | $3/1M | $6/1M | — | — | |
| Aion-3.0Aion LabsPrompt cachingJSON+2 | $6/1Mvia OpenRouter | 131K | $3/1M | $6/1M | — | — | |
| Fugu MaxSakana AIPrompt cachingJSON+3 | $6/1Mvia EmpirioLabs AI | 1M | $2/1M | $6/1M | — | 1K | |
| Grok 4.20 Beta 0309 Non ReasoningxAIPrompt cachingJSON+2 | $6/1Mvia AIHubMix | 1M | $2/1M | $6/1M | — | — | |
| Grok 4.20 Beta 0309 ReasoningxAIPrompt cachingJSON+3 | $6/1Mvia AIHubMix | 1M | $2/1M | $6/1M | — | — | |
 MiMo-V2-ProXiaomi | $6/1Mvia Jiekou.AI | — | $2/1M | $6/1M | 1436 | 2K | |
 Mistral LargeMistralPrompt cachingJSON+1 | $6/1Mvia OpenRouter | 128K | $2/1M | $6/1M | — | — | |
| Mistral Large 2407MistralNon-commercialPrompt caching+2 | $6/1Mvia OpenRouter | 131K | $2/1M | $6/1M | — | — | |
| Mistral-LargeMistralNon-commercial | $6/1Mvia AIHubMix | — | $2/1M | $6/1M | — | — | |
| Mixtral 8x22B InstructMistralPrompt cachingJSON+1 | $6/1Mvia OpenRouter | 66K | $2/1M | $6/1M | — | — | |
 Palmyra X5 (US)Writer | $6/1Mvia Amazon Bedrock | 1.04M | $0.60/1M | $6/1M | — | — | |
| Pixtral Large (25.02) (US)Mistral | $6/1Mvia Amazon Bedrock | — | $2/1M | $6/1M | 1089 | — | |
| Qwen3.5 Omni PlusAlibabaPrompt cachingJSON | $6/1Mvia APIYI | 256K | $1.40/1M | $8.30/1M | — | — | |
| Qwen3.8 Max PreviewAlibabaPrompt cachingJSON+3 | $6/1Mvia Charm Hyper | 262K | $2/1M | $6/1M | — | — | |
| Kimi K3.1 Pro HighspeedMoonshot AIPrompt cachingJSON+3 | $6.13/1Mvia Kenari | 1.05M | $1.81/1M | $9.44/1M | — | — | |
| Kimi K2.7 Code HighspeedMoonshot AIPrompt cachingJSON+3 | $6.17/1Mvia APIMart | 262K | $1.49/1M | $6.17/1M | — | — | |
| O4 Mini Deep ResearchOpenAI | $6.40/1Mvia APIMart | — | $1.60/1M | $6.40/1M | — | — | |
| OpenAI GPT-4.1OpenAIPrompt cachingJSON+2 | $6.40/1Mvia APIMart | 1.05M | $2/1M | $8/1M | 1383 | — |
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