# Taifoon – OpenAI-Compatible Chat Completion (openai-gpt-oss-120b via Venice AI)

> Taifoon – OpenAI-Compatible Chat Completion (openai-gpt-oss-120b via Venice AI) is a paid API for AI agents from coord.taifoon.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-28).

Runs a chat completion request against the openai-gpt-oss-120b model served by Venice AI with private inference, billed per token via x402 USDC micropayments, with a 3% Taifoon reseller markup.

## Facts

- Endpoint: POST https://coord.taifoon.dev/v1/chat/completions/openai-gpt-oss-120b?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/taifoon-openai-compatible-chat-completion-openai-gpt-oss-120b-via-109e8e25
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6ynnlB7mcxwZP-ZDnB7_7

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 taifoon-openai-compatible-chat-completion-openai-gpt-oss-120b-via-109e8e25 -d '<json body>'
```

Example prompt: Using the openai-gpt-oss-120b model, send this conversation: system says 'You are a helpful assistant', user asks 'Explain quantum entanglement in simple terms' — keep the reply under 500 tokens.

## When to prefer this

Choose this endpoint when you need private inference (Venice AI's confidentiality guarantees) on the openai-gpt-oss-120b model specifically, want per-call USDC micropayment billing via x402 (no subscription), and need OpenAI-compatible request/response format. It's a good fit for agents that handle sensitive data and prefer not to route through large public API providers. Prefer alternatives on this wall if you need models larger than 120b, streaming, or longer context windows beyond 700 output tokens.

## Known failure modes

- Insufficient USDC balance or failed x402 payment → payment error, request not processed
- max_tokens exceeds limit of 700 → validation error
- messages array empty or missing required role/content fields → 400 bad request
- Model identifier not recognized or unavailable → model not found error
- Venice AI upstream inference timeout or outage → 502/503 error
- Rate limiting by reseller or upstream provider → 429 too many requests

## How this service works

OpenAI-compatible chat completion on openai/gpt-oss-120b, served by DeepInfra (serverless inference) and sold by Taifoon at the provider's price plus a 76.47 % reseller cut: 0.07 / 0.3 USD per 1M tokens in/out. This request is priced at its prompt and max_tokens. The answer is checked before you are charged.

## Output

Returns an OpenAI-compatible chat completion JSON object containing the assistant's generated message, finish reason, model identifier, and token usage counts for prompt and completion tokens. The charge is only applied after the answer is verified.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "examples": [
    "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "deepseek-ai/DeepSeek-V4-Flash",
    "deepseek-v4-flash",
    "openai/gpt-oss-120b",
    "openai-gpt-oss-120b",
    "meta-llama/Llama-3.3-70B-Instruct",
    "Qwen/Qwen2.5-72B-Instruct",
    "deepseek-ai/DeepSeek-V3.2",
    "deepseek-v3.2",
    "z-ai/glm-5.3-flash",
    "Qwen/Qwen3-VL-30B-A3B-Instruct",
    "Qwen/Qwen3-235B-A22B-Instruct-2507"
   ],
   "description": "optional; one of the 22 models this wall delivers (GET lists them under terms.models); without it nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 answers"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant"
      ],
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "maxItems": 32,
   "minItems": 1
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 700,
   "minimum": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/taifoon-openai-compatible-chat-completion-openai-gpt-oss-120b-via-109e8e25/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from coord.taifoon.dev](https://www.zero.xyz/host/coord.taifoon.dev/llms.txt)