# Saylor Innovations LLM Model Pricing & Context Lookup

> Saylor Innovations LLM Model Pricing & Context Lookup is a paid API for AI agents from saylorinnovations.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-16).

Returns pricing (input/output USD per million tokens), context window sizes, and capability flags for LLM models from OpenAI, Anthropic, Google, and other providers

## Facts

- Endpoint: GET https://saylorinnovations.com/api/llm/models?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/saylor-innovations-llm-model-pricing-context-lookup-13dde3da
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GzCUXJA2foPPWR1QROPAX

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 saylor-innovations-llm-model-pricing-context-lookup-13dde3da
```

Example prompt: What's the input and output price per million tokens for gpt-4o, and how large is its context window? Search for 'gpt-4o' and return up to 5 results.

## When to prefer this

Use this endpoint when you need machine-readable LLM pricing, context window sizes, or capability metadata for one or more specific models — especially when comparing costs across providers like OpenAI, Anthropic, Google, or AWS Bedrock. Prefer this over manually checking provider docs when you need structured data that can be used in cost calculations or routing logic.

## Known failure modes

- Missing required query parameter 'q' returns an error
- Query string matches no models, returning matched=0 and an empty models array
- Provider filter typo returns no results
- Pricing data may be stale if checked_at timestamp is old
- Limit parameter outside 1-50 range may be rejected or clamped

## How this service works

LLM model pricing and context window lookup - input and output price per million tokens, max tokens and capabilities for OpenAI, Anthropic, Google and more

## Output

A JSON object containing the number of matched models and an array of model records, each with the model ID, provider, input and output USD cost per million tokens, cached input pricing, max input and output token counts, supported capability flags, deprecation date, the data source used, and the UTC timestamp when the data was last checked. A note field may provide caveats about the data.

## 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",
     "required": [
      "q"
     ],
     "properties": {
      "q": {
       "type": "string",
       "description": "Text the model id contains, e.g. gpt-4o, claude, gemini"
      },
      "limit": {
       "type": "string",
       "description": "optional 1-50, default 10"
      },
      "provider": {
       "type": "string",
       "description": "optional provider, e.g. openai, anthropic, gemini, bedrock"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "json"
    },
    "example": {
     "type": "object",
     "required": [
      "matched",
      "models"
     ],
     "properties": {
      "note": {
       "type": [
        "string",
        "null"
       ],
       "description": "Caveat or context for reading the result"
      },
      "query": {
       "description": "The query as the server interpreted it"
      },
      "models": {
       "type": "array",
       "items": {
        "type": "object",
        "properties": {
         "mode": {
          "description": "Mode used"
         },
         "model": {
          "type": "string",
          "description": "Model"
         },
         "provider": {
          "type": [
           "string",
           "null"
          ],
          "description": "Provider of the data"
         },
         "supports": {
          "type": "array",
          "items": {
           "type": "string"
          }
         },
         "deprecation_date": {
          "description": "Deprecation date"
         },
         "max_input_tokens": {
          "type": [
           "number",
           "null"
          ],
          "description": "Max input tokens"
         },
         "max_output_tokens": {
          "type": [
           "number",
           "null"
          ],
          "description": "Max output tokens"
         },
         "input_usd_per_1m_tokens": {
          "type": [
           "number",
           "null"
          ],
          "description": "
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/saylor-innovations-llm-model-pricing-context-lookup-13dde3da/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from saylorinnovations.com](https://www.zero.xyz/host/saylorinnovations.com/llms.txt)