# AgentRXI Kimi K2.6 Chat Completions

> AgentRXI Kimi K2.6 Chat Completions is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.018422/call, status unknown (last checked 2026-10-15).

Runs OpenAI-compatible chat completions using Moonshot Kimi K2.6, a 262K-context agentic LLM optimized for long tool-calling workflows, billed per token via x402.

## Facts

- Endpoint: GET https://agentrxi.com/v1/kimi/chat/completions?utm_source=zero.xyz
- Price: $0.018422/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-kimi-k2-6-chat-completions-615f93a8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vcrDIDyG_a2_0_hTC_Ts4

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 agentrxi-kimi-k2-6-chat-completions-615f93a8
```

Example prompt: Ask Kimi K2.6 to summarize this 50-page contract in plain English and flag any unusual indemnification clauses — use a system message that says 'You are a legal document analyst' and keep the response under 500 tokens.

## When to prefer this

Choose this endpoint when you need a large-context (262K tokens) agentic LLM that supports tool-calling workflows, want OpenAI SDK compatibility without creating an account or managing an API key, and prefer pay-per-token billing via x402 USDC micropayments. Ideal for agents that need to process long documents, run multi-step reasoning chains, or want to avoid subscription commitments. Prefer over OpenAI's own endpoint when x402 payment flow is already in use or when Kimi K2.6's strengths in agentic tasks are desired.

## Known failure modes

- Insufficient x402 payment budget causes 402 rejection before inference runs
- prompt parameter missing returns 400 bad request
- Exceeding 262K context window causes truncation or error
- Very long outputs may hit the max cost cap of $0.1742 per call
- Temperature or max_tokens values outside valid ranges may be rejected

## How this service works

OpenAI-compatible chat completions on Moonshot Kimi K2.6, an agentic model built for long tool-calling workflows (262K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/kimi and pay per token with x402 instead of an API key: $1.9 per million input and $8 per million output tokens, minimum $0.002 a call, at most $0.1742. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, re

## Output

Returns an OpenAI-format chat completion JSON object with the assistant's message content, role, finish_reason (e.g. 'stop'), token usage breakdown (prompt_tokens, completion_tokens, total_tokens), model name ('kimi-k2.6'), and a completion ID. Pricing is per actual tokens used when using 'upto' payment mode.

## 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": "kimi-k2.6",
  "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/agentrxi-kimi-k2-6-chat-completions-615f93a8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)