# Jatevo GPT-OSS 120B LLM Inference

> Jatevo GPT-OSS 120B LLM Inference is a paid API for AI agents from jatevo.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Runs chat and completion inference on a hosted 120B open-source language model with optional streaming, paid per-call in USDC.

## Facts

- Endpoint: POST https://jatevo.ai/api/x402/llm/gpt-oss
- 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/jatevo-ai-38a1cd9f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_StHg_DFz3H2zKVLy2Kpyw

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 jatevo-ai-38a1cd9f -d '<json body>'
```

Example prompt: Send a message to the GPT-OSS 120B model on Jatevo asking: 'Explain the concept of transformer attention in simple terms' — stream the response back as it's generated.

## When to prefer this

Choose this endpoint when you need inference from a large (120B) open-source language model with pay-per-call USDC pricing and no subscription commitment, especially when streaming responses are desirable and you want an alternative to proprietary LLMs.

## Known failure modes

- Missing required 'messages' or 'stream' fields returns 400 Bad Request
- Insufficient USDC balance or failed x402 payment returns 402 Payment Required
- Malformed message objects (missing role or content) cause validation errors
- Model overload or upstream inference failure may return 503 Service Unavailable
- Invalid boolean for 'stream' field causes request rejection

## How this service works

Hosted GPT-OSS 120B open-source language model via Jatevo for chat and completion inference (JSON POST with optional streaming); paid access via USDC on EIP-8453.

## Output

Returns a chat completion or streamed token sequence from the GPT-OSS 120B open-source language model, containing the assistant's generated response to the provided message history.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "stream",
  "messages"
 ],
 "properties": {
  "stream": {
   "type": "boolean"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/jatevo-ai-38a1cd9f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from jatevo.ai](https://www.zero.xyz/host/jatevo.ai/llms.txt)