Linkrra Synap

Linkrra Synap: Qwen3 30B A3B Instruct 2507 (model "qwen/qwen3-30b-a3b") - general, high-throughput. OpenAI-compatible chat completions for this one model, 64K context, served only on our own GPUs, 4-bit AWQ. Pay per call in USDC on Base via x402 - no account, no API key. From $0.001 per call, usage-priced per token above that (GET /v1/models). Streaming supported. Product site: https://synap.linkrra.com

Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.

Endpoint

POST https://pool.linkrra.com/api/billing/x402/models/qwen3-30b-a3b/chat/completions

Our checks, last 30 days

Example input (from the provider)

{
  "body": {
    "max_tokens": 256,
    "messages": [
      {
        "content": "Write a Python function that reverses a string",
        "role": "user"
      }
    ],
    "model": "qwen/qwen3-30b-a3b",
    "stream": false
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

Promised output schema (from the provider)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "input": {
      "additionalProperties": false,
      "properties": {
        "body": {
          "properties": {
            "max_tokens": {
              "default": 4096,
              "description": "Completion token cap. The price is quoted for the prompt plus this cap.",
              "maximum": 4096,
              "minimum": 1,
              "type": "integer"
            },
            "messages": {
              "description": "OpenAI-format chat history, oldest first: [{role, content}].",
              "examples": [
                [
                  {
                    "content": "Write a Python function that reverses a string",
                    "role": "user"
                  }
                ]
              ],
              "items": {
                "properties": {
                  "content": {
                    "description": "Text, or an array of OpenAI content parts."
                  },
                  "role": {
                    "enum": [
                      "system",
                      "user",
                      "assistant",
                      "tool"
                    ],
                    "type": "string"
                  }
                },
                "required": [
                  "role",
                  "content"
                ],
                "type": "object"
              },
              "minItems": 1,
              "type": "array"
            },
            "model": {
              "description": "Optional: this endpoint always runs qwen/qwen3-30b-a3b.",
              "enum": [
                "qwen/qwen3-30b-a3b"
              ],
              "type": "string"
            },
            "stream": {
              "default": false,
              "description": "true = stream OpenAI-format Server-Sent Events.",
              "type": "boolean"
            }
          },
          "required": [
            "messages"
          ],
          "type": "object"
        },
        "bodyType": {
          "enum": [
            "json"
          ],
          "type": "string"
        },
        "method": {
          "enum": [
            "POST"
          ],
          "type": "string"
        },
        "type": {
          "const": "http",
          "type": "string"
        }
      },
      "required": [
        "type",
        "method",
        "bodyType",
        "body"
      ],
      "type": "object"
    },
    "output": {
      "description": "200 chat.completion (SSE if stream=true). 402 payment required or insufficient (challenge in PAYMENT-REQUIRED). 202 settlement pending. 400 invalid body or payment header. 404 model not offered. 409 payment already used. 503 no node serving the model, nothing charged. 500/502 facilitator, chain or model-server error; if inference fails after settlement the amount stays credited to the paying wallet.",
      "properties": {
        "example": {
          "properties": {
            "choices": {
              "description": "choices[0].message.content is the reply.",
              "type": "array"
            },
            "model": {
              "description": "The model that answered.",
              "type": "string"
            },
            "payment": {
              "description": "USDC paid + Base tx hash; any unused amount stays credited to the payer.",
              "type": "object"
            },
            "usage": {
              "description": "Tokens billed: prompt, completion, total.",
              "type": "object"
            }
          },
          "type": "object"
        },
        "type": {
          "type": "string"
        }
      },
      "required": [
        "type",
        "example"
      ],
      "type": "object"
    }
  },
  "required": [
    "input",
    "output"
  ],
  "type": "object"
}

This page as JSON