# modelprices.xyz Cheapest Reasoning Model Leaderboard

> modelprices.xyz Cheapest Reasoning Model Leaderboard is a paid API for AI agents from modelprices.xyz, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

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.

## Facts

- Endpoint: GET https://modelprices.xyz/llm/cheapest/reasoning
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/modelprices-xyz-cheapest-reasoning-model-leaderboard-cb1041ee
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_74nbfbDM05bvtW90WJ_UC

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability modelprices-xyz-cheapest-reasoning-model-leaderboard-cb1041ee
```

Example prompt: 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?

## When to prefer this

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.

## Known failure modes

- 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

## How this service works

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.

## Output

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.

## Request schema (JSON Schema)

```json
{
 "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"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/modelprices-xyz-cheapest-reasoning-model-leaderboard-cb1041ee/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from modelprices.xyz](https://www.zero.xyz/host/modelprices.xyz/llms.txt)