Cheapest LLM API
738 text models sorted by the lowest output price per 1M tokens across every provider, with their quality score beside it.
/
 Qwen Deep ResearchAlibaba | $23.37/1Mvia Alibaba | — | $7.74/1M | $23.37/1M | — | — | |
| OpenAI GPT-5.5OpenAIPrompt cachingJSON+3 | $24/1Mvia APIMart | 1.05M | $5/1M | $30/1M | 1513 | — | |
| Claude Opus 4.6Anthropic | $25/1Mvia Helicone | — | $5/1M | $25/1M | — | — | |
| GPT-6 AstraOpenAIPrompt cachingJSON+3 | $25/1Mvia CrazyRouter | 1.05M | $10/1M | $50/1M | 1775 | 580K | |
| Grok 3 FastxAI | $27.50/1Mvia AIHubMix | — | $5.50/1M | $27.50/1M | — | — | |
| Chat Latest (GPT-5.5 Instant)OpenAIPrompt cachingVision | $30/1Mvia ZenMux | 400K | $5/1M | $30/1M | 1419 | — | |
 Fugu UltraSakana AIPrompt cachingJSON+3 | $30/1Mvia EmpirioLabs AI | 1M | $5/1M | $30/1M | — | — | |
| Fugu Ultra v2.0Sakana AIPrompt cachingJSON+3 | $30/1Mvia EmpirioLabs AI | 1M | $5/1M | $30/1M | — | — | |
| GPT 5.6 SolOpenAI | $30/1Mvia Atlas Cloud | — | $5/1M | $30/1M | — | — | |
| GPT-4 TurboOpenAIJSONTool calling+1 | $30/1Mvia AI/ML API | 128K | $10/1M | $30/1M | 1272 | — | |
| GPT-5.6OpenAI | $30/1Mvia Prime Inference | — | $5/1M | $30/1M | — | 26K | |
| Kimi Thinking PreviewMoonshot AI | $30/1Mvia AIHubMix | — | $30/1M | $30/1M | — | — | |
| Fugu Ultra v1.1Sakana AIPrompt cachingVision | $30.30/1Mvia Poe | 1M | $5.05/1M | $30.30/1M | — | — | |
| O3 Deep ResearchOpenAI | $32/1Mvia APIMart | — | $8/1M | $32/1M | — | — | |
| Claude 2.1Anthropic | $39.60/1Mvia AIHubMix | — | $8.80/1M | $39.60/1M | — | — | |
| Claude Fable 5AnthropicPrompt cachingJSON+3 | $40/1Mvia APIMart | 1M | $10/1M | $50/1M | 1624 | 35K | |
| Claude Fable 5.1AnthropicPrompt cachingJSON+3 | $40/1Mvia APIMart | 1M | $10/1M | $50/1M | 1743 | 34K | |
| Claude Mythos 5Anthropic | $40/1Mvia CometAPI | — | $10/1M | $50/1M | — | — | |
| GPT 5.6 Sol ProOpenAIPrompt cachingVision | $40/1Mvia AIHubMix | 1.05M | $8/1M | $40/1M | — | — | |
| O1 PreviewOpenAIPrompt cachingReasoning+1 | $48/1Mvia APIMart | — | $12/1M | $48/1M | — | — | |
| OpenAI o1OpenAIPrompt cachingJSON+3 | $48/1Mvia APIMart | 200K | $15/1M | $60/1M | 1366 | — | |
| Claude Mythos 5.1Anthropic | $50/1Mvia Anthropic | — | $10/1M | $50/1M | — | — | |
| GPT 6 Astra CodexOpenAI | $50/1Mvia Atlas Cloud | — | $10/1M | $50/1M | — | — | |
| GPT-6 Astra Pro ($$$$)OpenAIPrompt cachingJSON+3 | $50/1Mvia OpenRouter | 1.05M | $10/1M | $50/1M | — | — | |
| Daybreak RedOpenAI | $60/1Mvia CometAPI | — | $12.50/1M | $75/1M | — | — | |
| GPT-4OpenAIJSONTool calling | $60/1Mvia AI/ML API | 8K | $30/1M | $60/1M | 1206 | 43K | |
| O3 ProOpenAIJSONReasoning+2 | $64/1Mvia APIMart | 200K | $20/1M | $80/1M | — | — | |
| Claude 3 OpusAnthropic | $75/1Mvia Amazon Bedrock | — | $15/1M | $75/1M | 1262 | — | |
| Claude Opus 4AnthropicPrompt cachingJSON+3 | $75/1Mvia Atlas Cloud | 200K | $15/1M | $75/1M | 1377 | — | |
| Claude Opus 4.1AnthropicPrompt cachingReasoning+2 | $75/1Mvia AI/ML API | 200K | $15/1M | $75/1M | — | — | |
| GPT-5.5 CyberOpenAI | $75/1Mvia OpenAI | — | $12.50/1M | $75/1M | — | — | |
| GPT-5 ProOpenAIJSONReasoning+2 | $96/1Mvia APIMart | 400K | $15/1M | $120/1M | — | — | |
| GPT-6 Astra (Fast)OpenAIPrompt cachingJSON+3 | $100/1Mvia Vercel AI Gateway | 1.05M | $20/1M | $100/1M | — | — | |
| OpenAI GPT-5.2 ProOpenAIJSONReasoning+2 | $134.40/1Mvia APIMart | 400K | $21/1M | $168/1M | — | — | |
| Claude Mythos PreviewAnthropic | $137.50/1Mvia Amazon Bedrock | — | $27.50/1M | $137.50/1M | — | — | |
| GPT-5.5 ProOpenAIJSONReasoning+2 | $144/1Mvia CometAPI | 1.05M | $30/1M | $180/1M | — | — | |
| OpenAI GPT-5.4 ProOpenAIJSONReasoning+2 | $144/1Mvia APIMart | 1.05M | $30/1M | $180/1M | — | — | |
| O1 ProOpenAIJSONReasoning+1 | $480/1Mvia APIMart | 200K | $150/1M | $600/1M | — | — |
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