# modelprices.xyz LLM Limits & Capabilities Table

> modelprices.xyz LLM Limits & Capabilities Table is a paid API for AI agents from modelprices.xyz, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-12).

Returns a comprehensive table of capability specs and constraints for 2,000+ LLMs, including context window size, max output tokens, and feature support flags (vision, audio, function-calling, reasoning).

## Facts

- Endpoint: GET https://modelprices.xyz/llm/limits?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/modelprices-xyz-llm-limits-capabilities-table-4ed49234
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QO1yjq6bMCepkuJcB7lHi

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-llm-limits-capabilities-table-4ed49234
```

Example prompt: Show me a full comparison table of all LLMs — including context window size, max output tokens, and whether they support vision, audio, function-calling, and reasoning — so I can pick the right model for a long-context multimodal task.

## When to prefer this

Use this endpoint when you need to compare capability constraints (context window, max tokens, feature flags) across many models at once, rather than looking up a single model. Ideal for automated model-selection logic that must filter 2,000+ models by capability. Prefer over single-model lookup when the model name is not yet known and you need to search or filter the full catalog.

## Known failure modes

- Payment not completed — 402 response if x402 payment header is missing or invalid
- Rate limit exceeded — too many requests in a short window
- Service temporarily unavailable — upstream data refresh failure
- Malformed response if query parameters are unexpected

## How this service works

Per-token prices, capability limits, and a price-change feed for 2,000+ LLMs across 70+ providers, normalized into single JSON tables and refreshed hourly.

## Output

A table of 2,000+ LLM entries refreshed hourly, each row containing the model name, provider, context window size (in tokens), maximum output tokens, and boolean capability flags for vision, audio, function-calling, and reasoning support. Useful for programmatic model selection based on capability constraints.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "models": [
   {
    "id": "claude-sonnet-5",
    "provider": "anthropic",
    "input_per_mtok": 3,
    "output_per_mtok": 15
   }
  ],
  "model_count": 2164,
  "generated_at": "2026-07-14T02:00:00.000Z",
  "provider_count": 72
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/modelprices-xyz-llm-limits-capabilities-table-4ed49234/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)