# Telnyx Inference – Kimi K2.6 Long-Context Chat Completions

> Telnyx Inference – Kimi K2.6 Long-Context Chat Completions is a paid API for AI agents from x402.telnyx.com, paid per call via x402, $0.079376/call, status unknown (last checked 2026-10-15).

Generates OpenAI-compatible chat completions using Moonshot AI's Kimi K2.6 model with a 200K-character input window, suitable for very long documents and conversations.

## Facts

- Endpoint: POST https://x402.telnyx.com/v1/chat/completions/_t/kimi-long/upto?utm_source=zero.xyz
- Price: $0.079376/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/telnyx-inference-kimi-k2-6-long-context-chat-completions-dff54b8e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_G6EVR5NYOCtUJuXhMR0yE

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 telnyx-inference-kimi-k2-6-long-context-chat-completions-dff54b8e -d '<json body>'
```

Example prompt: I have a 150,000-character legal contract I need you to review and summarize the key obligations and risks — use the Kimi K2.6 long-context model through Telnyx Inference so the whole document fits in one call.

## When to prefer this

Choose this endpoint when you need to process very long inputs — documents, codebases, conversation histories, or research papers — that exceed the context windows of standard LLMs. It is ideal when the full 200K-character window is needed in a single API call rather than chunking. Prefer it over shorter-context siblings when document integrity is important and you cannot afford information loss from splitting. The metered x402 payment model makes it suitable for agents that pay per call without subscription overhead.

## Known failure modes

- Message content exceeding 200,000 characters per message returns a validation error
- More than 64 messages in the messages array will be rejected
- More than 16 tools in the tools array will be rejected
- Payment failure or insufficient USDC balance results in a 402 Payment Required response
- Model unavailability or overload may cause 503 or timeout errors
- Malformed message roles (not system/user/assistant/tool) will cause a 422 validation error

## How this service works

Long-context chat completions via Telnyx Inference (Kimi K2.6) — 200K-char input window, 2048-token output. OpenAI-compatible. $0.0543 USDC per call. (upto metered — large context)

## Output

An OpenAI-compatible chat completion response containing one generated assistant message, with optional tool call objects if tools were defined. The response includes the model's text output (up to 8192 tokens), usage statistics, and finish reason.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "n": {
   "type": "integer",
   "const": 1,
   "description": "Fixed to one completion per paid call."
  },
  "model": {
   "type": "string",
   "const": "moonshotai/Kimi-K2.6-long",
   "description": "Model identifier; fixed to moonshotai/Kimi-K2.6-long on this route."
  },
  "tools": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "maxItems": 16
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant",
       "tool"
      ],
      "type": "string"
     },
     "content": {
      "type": "string",
      "maxLength": 200000
     }
    }
   },
   "maxItems": 64,
   "description": "OpenAI-style chat messages."
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 8192,
   "minimum": 1
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/telnyx-inference-kimi-k2-6-long-context-chat-completions-dff54b8e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.telnyx.com](https://www.zero.xyz/host/x402.telnyx.com/llms.txt)