ARAgentRouter
MODEL CATALOG

Prices per 1M tokens.

USD. Input and output shown separately. No tiers.

Source
GET /v1/models
Display
USD / 1M tokens

Raw catalog response and the public request are rendered below from the same source as the human table.

Model catalog

Build-time snapshot retrieved . Prices and availability may change.Check the live catalog ↗

Sorted by model, ascending.

Available language models, compatible API protocols, context windows, and prices in US dollars per one million tokens.
zai/glm-5.3Aliases: glm-5.3
anthropicopenai
131Ktokens
Max output: 131,072
$1.4/ 1M tokens
Cache read: $0.26 / 1M
Cache write: $0 / 1M
$4.4/ 1M tokens

Purchase-funded keys use the current API sell prices at request time. Buy inference

Machine-readable pricing catalog

AGENT PATH

One endpoint, one catalog shape, decimal-string prices.

GET MODEL CATALOG
curl -sS https://api.agentrouter.cc/v1/models
EXPECTED CATALOG · JSON SCHEMA
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "HTTP 200 public model catalog body",
  "type": "array",
  "items": {
    "type": "object",
    "required": ["id", "input_per_1m", "output_per_1m", "context_length", "max_output_tokens", "protocols"],
    "properties": {
      "id": { "type": "string" },
      "aliases": { "type": "array", "items": { "type": "string" } },
      "input_per_1m": { "type": "string" },
      "output_per_1m": { "type": "string" },
      "cache_read_per_1m": { "type": "string" },
      "cache_write_per_1m": { "type": "string" },
      "free": { "type": "boolean" },
      "context_length": { "type": "integer" },
      "max_output_tokens": { "type": "integer" },
      "protocols": {
        "type": "array",
        "items": { "type": "string", "enum": ["openai", "anthropic"] }
      }
    }
  }
}
CATALOG JSON
[
  {
    "id": "zai/glm-5.3",
    "protocols": [
      "anthropic",
      "openai"
    ],
    "context_length": 131072,
    "max_output_tokens": 131072,
    "input_per_1m": "1.4",
    "output_per_1m": "4.4",
    "aliases": [
      "glm-5.3"
    ],
    "cache_read_per_1m": "0.26",
    "cache_write_per_1m": "0"
  }
]
TESTNET · BASE SEPOLIA

Try the whole flow with testnet funds.

Real inference, paid with testnet tokens.