# Oblique Markets LLM Inference Proxy

> Oblique Markets LLM Inference Proxy is a paid API for AI agents from api.oblique.markets, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Routes LLM inference requests through a fixed-price $0.01 Base rail proxy, enabling AI agents to pay-per-call for language model completions via x402

## Facts

- Endpoint: POST https://api.oblique.markets/api/v1/paid/inference
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/oblique-markets-llm-inference-proxy-d1c51918
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lq1_BoXlcxLI8ZTkt8XsE

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 oblique-markets-llm-inference-proxy-d1c51918 -d '<json body>'
```

Example prompt: Run an LLM inference query through Oblique Markets and charge it to my Base wallet — I want to ask: 'Summarize the key risks of investing in small-cap DeFi tokens' and get back the model's response.

## When to prefer this

Choose this endpoint when your agent needs LLM inference paid via crypto micropayments on Base using the x402 protocol, especially in autonomous agent pipelines where credit-card billing is impractical. Ideal for pay-as-you-go AI inference without subscription overhead, and when operating within the Oblique Markets ecosystem alongside their on-chain analytics and research tools.

## Known failure modes

- Insufficient USDC balance on Base — payment fails and request is rejected with 402
- Malformed query parameters — returns 400 with schema validation error
- Unsupported HTTP method (e.g. POST) — schema enforces GET/HEAD/DELETE only
- Upstream LLM provider outage — proxy may return 503 or timeout
- Rate limiting or quota exceeded — returns 429 if too many calls in a short window

## How this service works

Use when an agent wants a chat completion paid per call with no API key, on Base or Solana. Returns Chat completion from one of six catalogued models in the standard messages request shape, with token usage and the settled charge. $1.00 maximum on Base; $0.01 fixed on Solana. Rail: $0.01 fixed on Base.

## Output

Returns the LLM-generated text completion or inference result for the submitted prompt, delivered as an HTTP response after the x402 micropayment on the Base rail is settled.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "description": "Model ID (see /api/v1/models)"
  },
  "stream": {
   "type": "boolean",
   "description": "Enable SSE streaming"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "description": "Chat messages array"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "gen-1789171942-4eZlZ1R9FNzHB7l9nTCc",
  "model": "deepseek/deepseek-v4-flash",
  "usage": {
   "cost": 0.00000252,
   "total_tokens": 19,
   "prompt_tokens": 10,
   "completion_tokens": 9
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "Hello! How can I help you?"
    },
    "finish_reason": "stop"
   }
  ],
  "created": 1789171942,
  "payment_info": {
   "message": "Fixed-price payment settled via x402 protocol",
   "charged_usdc": 0.01,
   "payment_scheme": "exact",
   "authorized_max_usdc": 0.01,
   "usage_cost_estimate_usd": 0.000011
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/oblique-markets-llm-inference-proxy-d1c51918/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.oblique.markets](https://www.zero.xyz/host/api.oblique.markets/llms.txt)