Kimi K2.7 Code API — pricing & examples

Models/Chat/Kimi K2.7 Code

ChatReasoningCodingTool calling262K context

Context window

262K tokens

Modality

Text → Text

Input

$0.89 / 1M tokens

Cached input

$0.18 / 1M tokens

Output

$4.42 / 1M tokens

Time to first token

0.87 s

First answer word

37.34 s at default reasoning

Output speed

40.7 tok/s

Model ID

moonshotai/Kimi-K2.7-Code

Quickstart

You need an API key to call this model. Create a free account or log in.

Set INFERENCE_API_KEY to your key from the API Keys page, then run:

curl https://api.inferenceapis.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/Kimi-K2.7-Code",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferenceapis.com/v1",
    api_key=os.environ["INFERENCE_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.7-Code",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! What can you do?"},
    ],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferenceapis.com/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "moonshotai/Kimi-K2.7-Code",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello! What can you do?" },
  ],
});
console.log(response.choices[0].message.content);

When to use it

A good fit when

Coding agents: it is the coding-tuned model of Moonshot's Kimi family

Look elsewhere when

You need full-precision weights; our upstream serves this model at FP4

What it costs in practice

Workload	Cost
Chat assistant — 10,000 turns of 800 tokens in, 300 out	$20.38
Long prompts or RAG — 10,000 requests of 8,000 in, 500 out	$93.30
Generation-heavy — 10,000 requests of 500 in, 2,000 out	$92.85

Computed from the live rates below. This is a reasoning model, and thinking is billed as output, so real output counts run above the visible answer; see controlling reasoning to keep that down. There is no subscription or minimum; new accounts start with free credit.

Endpoint

POST https://api.inferenceapis.com/v1/chat/completions

Headers Authorization: Bearer $INFERENCE_API_KEY
Content-Type: application/json

Compatible OpenAI wire format. /openai/v1/… is accepted too, so Groq-style base URLs work with only the host changed.

Model IDs and aliases

Send any of these as model; they all resolve to this model and bill at its rate.

ID	Note
`moonshotai/Kimi-K2.7-Code`	Canonical
`kimi-k2.7-code`	Alias

Request body

Parameter	Type	Description
`model` required	string	Model ID: `moonshotai/Kimi-K2.7-Code` — also accepted: `kimi-k2.7-code`
`messages` required	array	Conversation so far. Each item has a `role` (`system`, `user` or `assistant`) and `content`.
`max_tokens`	integer	Maximum number of tokens to generate (includes reasoning tokens — use a few hundred or more).
`temperature`	number	Sampling temperature. Higher values give more varied output.
`top_p`	number	Nucleus sampling cutoff.
`stream`	boolean	Stream the response as server-sent events. The final chunk includes `usage`.
`tools`	array	Tool definitions for function calling (OpenAI format).
`response_format`	object	`{"type": "json_object"}` for JSON mode.
`stop`	string \| array	Sequences where the model stops generating.
`seed`	integer	Seed for more reproducible sampling.

Response

200 OK · application/json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "moonshotai/Kimi-K2.7-Code",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! I can answer questions, write and edit text, help with code and more.",
        "reasoning": "The user is greeting me and asking about capabilities..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 28, "completion_tokens": 17, "total_tokens": 45 }
}

Controlling reasoning

Send reasoning_effort: "none" to switch thinking off. On our test question this model used 29 completion tokens by default and 2 with thinking off, and the answer started immediately instead of after the reasoning. Model families disagree on the parameter for this, and the wrong one is silently ignored, so the gateway accepts one spelling on every model (also "minimal", reasoning: {"enabled": false} and thinking: {"type": "disabled"}) and sends the switch this model honours; the X-Thinking: off response header confirms it. On the Responses API use reasoning: {"effort": "minimal"}. Leave thinking on for multi-step coding and maths; turn it off for extraction, classification, routing and chat. All models compared.

Python · openai SDK

resp = client.chat.completions.create(
    model="moonshotai/Kimi-K2.7-Code",
    reasoning_effort="none",        # thinking off; omit it to let the model reason
    messages=[{"role": "user", "content": "Extract the invoice number from: ..."}],
    max_tokens=500,
)
print(resp.choices[0].message.content)

Token counts are single measurements from September 17, 2026 and vary with the question; the direction is what matters.

Tested on this endpoint

Tool calling (`tools`, `tool_calls`)	Works
JSON mode (`response_format: json_object`)	Not supported
Schema-constrained output (`response_format: json_schema`)	Not supported
Streaming with `usage` in the final chunk	Works
System prompt followed	Works
Reasoning tokens reported in `usage`	Not supported

Each row is a live request we sent on September 17, 2026, not a claim copied from a model card. Streamed and parallel tool calls and tool_choice were tested too: full matrix for every model. Request examples are in the API documentation.

Pricing

Input	$0.89 / 1M tokens
Cached input	$0.18 / 1M tokens
Output	$4.42 / 1M tokens
Billing	Pay as you go from prepaid credits. No subscription, no daily request or token cap. See all pricing.

Notes

It thinks for a long time: on a simple 120-word writing prompt it spent about 37 seconds before the first visible word in our measurement. Stream the response, and keep it for coding tasks where that thinking pays off.
Tool calling passed our test. JSON mode did not: with response_format set, the JSON arrived in reasoning_content and content was empty. Ask for JSON in the prompt instead, or use a model where JSON mode is verified.
Served at FP4 precision by the upstream provider.
The thinking is returned in reasoning_content; the upstream does not report a separate reasoning-token count for this model.

Compare Kimi K2.7 Code with…

GPT-OSS 120B DeepSeek V4 Flash DeepSeek V4.1 Flash GLM 5.3 Flash Llama 3.3 70B Instruct GLM 5.3 DeepSeek V4 Pro MiniMax M3 Qwen3-VL 235B GPT-OSS 120B on Groq Llama 3.3 70B on Groq GPT-4o mini GPT-4.1 mini Gemini 2.5 Flash DeepSeek V4 Flash (DeepSeek API)

Errors

Errors use the OpenAI envelope: {"error": {"message", "type", "code"}}. 401 missing or invalid key · 402 insufficient_balance · 404 model_not_found · 503 model_unavailable · 502 backend error, safe to retry. Full table with what to retry: API documentation. Errors from other providers: provider error reference.