{"uid":"cap_74nbfbDM05bvtW90WJ_UC","slug":"modelprices-xyz-cheapest-reasoning-model-leaderboard-cb1041ee","name":"modelprices.xyz Cheapest Reasoning Model Leaderboard","description":"Cheapest reasoning-model leaderboard: the 50 lowest-cost AI models with extended reasoning / chain-of-thought support, ranked by inference cost per token — o3, Claude 5 thinking, Gemini 3 Pro, DeepSeek R1, Qwen QwQ and more across 70+ providers. Input, output and cache USD per 1M tokens with context windows joined in. Refreshed hourly.","url":"https://modelprices.xyz/llm/cheapest/reasoning","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vFrYbl2FLCIbGuSNjQBgU","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns the 50 lowest-cost AI models with extended reasoning/chain-of-thought support, ranked by inference cost per token, including input/output/cache pricing and context window sizes across 70+ providers.","exampleAgentPrompt":"What are the 50 cheapest AI models that support extended reasoning or chain-of-thought right now, ranked by cost per token — include input, output, and cache prices plus context window sizes?","exampleUseCases":[{"title":"Cost-optimize a reasoning pipeline","prompt":"I'm building an agent that needs to do multi-step reasoning but I want to keep inference costs low — can you pull the current leaderboard of the cheapest reasoning models so I can pick one that fits my budget?"},{"title":"Compare top reasoning model prices","prompt":"How does DeepSeek R1 compare price-wise to o3, Claude thinking, and QwQ right now? Pull the cheapest reasoning model leaderboard so I can see them side by side."},{"title":"Scout affordable CoT models for a startup","prompt":"We're a small team and can't afford expensive models — show me the cheapest reasoning models with chain-of-thought support available today across all major providers, ranked by cost per million tokens."}],"resultDescription":"A ranked list of up to 50 AI models with reasoning/chain-of-thought support, ordered from cheapest to most expensive by inference cost. Each entry includes the model name, provider, input cost (USD per 1M tokens), output cost (USD per 1M tokens), cache cost where applicable, and context window size. Data is refreshed hourly.","failureModes":["Payment failure (402) if USDC not provided or insufficient balance","Upstream pricing data temporarily unavailable causing stale or empty response","Rate limiting if called too frequently","Network timeout if provider aggregation takes too long"],"whenToPreferThis":"Use this endpoint when you need a comprehensive, up-to-date ranking of the cheapest reasoning/CoT models across all major providers in a single call. Prefer this over individual provider pricing tables (e.g. the OpenAI or AWS Bedrock endpoints on modelprices.xyz) when you want cross-provider comparison specifically filtered to reasoning-capable models. Best when cost optimization for chain-of-thought inference is the primary goal.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:49:46.406Z","isFirstParty":false}