# Citiview GPT-OSS-20B Chat Completions

> Citiview GPT-OSS-20B Chat Completions is a paid API for AI agents from agents.citiviewgroup.com, paid per call via x402, $0.003856/call, status unknown (last checked 2026-10-14).

OpenAI-compatible chat completions via a pay-per-request open-weight reasoning model with tool calling and streaming support

## Facts

- Endpoint: GET https://agents.citiviewgroup.com/v1/gpt-oss-20b/chat/completions?utm_source=zero.xyz
- Price: $0.003856/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/citiview-gpt-oss-20b-chat-completions-3ed6e894
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Hu4Q32ZA-iyIfSQ1Teoak

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 citiview-gpt-oss-20b-chat-completions-3ed6e894
```

Example prompt: Ask the GPT-OSS-20B reasoning model: 'What are the key tradeoffs between microservices and monolithic architectures?' — use a system message saying 'You are a senior software architect' and keep the response under 512 tokens.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible chat completions on a pay-per-request basis without API key registration, especially when using the OpenAI SDK and wanting to swap in an open-weight reasoning model with tool calling. Prefer it over managed OpenAI when you want per-call micropayments via x402 USDC, no subscription commitment, or access to an open-weight model with comparable interface semantics.

## Known failure modes

- Missing required 'prompt' query parameter returns a 400 error
- Payment failure or insufficient USDC balance returns a 402 Payment Required
- Prompt exceeds model context window returns a 400 or 413 error
- Invalid temperature or max_tokens values may return a 422 validation error
- Model overload or timeout may return a 503 or 504 error
- Streaming connection drops mid-response can leave incomplete output

## How this service works

Citiview Agent Market: 211 pay-per-call tools for AI agents. Cited answers, deep research, agent memory, file hosting, webhooks, schedules, sanctions and link safety checks, OpenAI-compatible LLMs on 11 models, web search, scraping, PDF, OCR, speech, Solana and EVM token risk, DeFi, prediction odds, SEC data. Pay per call in USDC with x402. No key, no signup.

## Output

Returns an OpenAI-compatible chat completion object containing the model's generated response text, up to 4096 output tokens, and optionally tool call payloads or streamed chunks if streaming is enabled.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "prompt"
     ],
     "properties": {
      "prompt": {
       "type": "string",
       "description": "User message"
      },
      "system": {
       "type": "string",
       "description": "Optional system message"
      },
      "max_tokens": {
       "type": "integer"
      },
      "temperature": {
       "type": "number"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-...",
  "model": "gpt-oss-20b",
  "usage": {
   "total_tokens": 18,
   "prompt_tokens": 14,
   "completion_tokens": 4
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "Bonjour !"
    },
    "finish_reason": "stop"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/citiview-gpt-oss-20b-chat-completions-3ed6e894/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.citiviewgroup.com](https://www.zero.xyz/host/agents.citiviewgroup.com/llms.txt)