GET

/v1/ai/models

Models available for inference. Billing is metered: each call costs what it uses. Each model lists its price per 1M input and output tokens (price_per_million_usd), what a typical question costs (question_estimate_cents, also as cost_cents), and its published intelligence index (Artificial Analysis, reconciled against OpenRouter's benchmarks API)

AuthNone — works without a key

Request

GEThttps://api.xrpl.to/v1/ai/models

curl 'https://api.xrpl.to/v1/ai/models'

Response

200Example response13 ms · just now · 3.1 KB · 151 lines

https://api.xrpl.to/v1/ai/models

{
  "models": [
    {
      "id": "z-ai/glm-5.3-flash",
      "provider": "openrouter",
      "cost_cents": 3.075,
      "question_estimate_cents": 3.075,
      "price_per_million_usd": {
        "input": 0.75,
        "output": 2.5
      },
      "intelligence_index": 41.9,
      "coding_index": 71.5,
      "agentic_index": 51.2,
      "reasoning": true,
      "thinking": {
        "auto": "high",
        "fast": "low",
        "balanced": "high",
        "deep": "max",
        "efforts": [
          "low",
          "high",
          "max"
        ]
      },
      "context_window": 1310720
    },
    {
      "id": "z-ai/glm-5.3",
      "provider": "openrouter",
      "cost_cents": 28.5,
      "question_estimate_cents": 28.5,
      "price_per_million_usd": {
        "input": 7,
        "output": 22
      },
      "intelligence_index": 44.9,
      "coding_index": 74.8,
      "agentic_index": 53.4,
      "reasoning": true,
      "thinking": {
        "auto": "max",
        "fast": "low",
        "balanced": "high",
        "deep": "max",
        "efforts": [
          "low",
          "high",
          "max"
        ]
      },
      "context_window": 1310720
    },
    {
      "id": "qwen/qwen3.8-max-0902",
      "provider": "openrouter",
      "cost_cents": 40.5,
      "question_estimate_cents": 40.5,
      "price_per_million_usd": {
        "input": 10,
        "output": 30
      },
      "intelligence_index": 53.4,
      "coding_index": 68.9,
      "agentic_index": 49.9,
      "reasoning": true,
      "thinking": {
        "auto": "xhigh",
        "fast": "minimal",
        "balanced": "medium",
        "deep": "xhigh",
        "efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh"
        ]
      },
      "context_window": 1000000
    },
    {
      "id": "moonshotai/kimi-k2.6",
      "provider": "openrouter",
      "cost_cents": 14.2575,
      "question_estimate_cents": 14.2575,
      "price_per_million_usd": {
        "input": 3.25,
        "output": 17.05
      },
      "intelligence_index": 27.5,
      "coding_index": 61.8,
      "agentic_index": 20.5,
      "reasoning": true,
      "context_window": 262144
    },
    {
      "id": "moonshotai/kimi-k3",
      "provider": "openrouter",
      "cost_cents": 65.25,
      "question_estimate_cents": 65.25,
      "price_per_million_usd": {
        "input": 15,
        "output": 75
      },
      "intelligence_index": 43.8,
      "coding_index": 76.2,
      "agentic_index": 50.6,
      "reasoning": true,
      "thinking": {
        "auto": "max",
        "fast": "low",
        "balanced": "high",
        "deep": "max",
        "efforts": [
          "low",
          "high",
          "max"
        ]
      },
      "context_window": 1048576
    }
  ],
  "packs": [
    {
      "id": "mini",
      "name": "Mini",
      "usd": 2.5,
      "cents": 250
    },
    {
      "id": "starter",
      "name": "Starter",
      "usd": 5,
      "cents": 500
    },
    {
      "id": "standard",
      "name": "Standard",
      "usd": 20,
      "cents": 2000
    },
    {
      "id": "pro",
      "name": "Pro",
      "usd": 50,
      "cents": 5000
    }
  ]
}

Long arrays and strings are shortened in the example; Send request for the full answer.

What it does

OpenAPI