Does Kimi K2.7-Code support streaming?

Yes—at least one listed provider advertises streaming.

What are limitations of Kimi K2.7-Code?

Like other API models, Kimi K2.7-Code can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.

What modalities does Kimi K2.7-Code support?

Kimi K2.7-Code accepts text, image, video and produces text according to its architecture metadata on LLM.API.

How do I call Kimi K2.7-Code via API?

Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "kimi-k2.7-code" and your LLM.API key. See the code snippet on this page.

Which providers serve Kimi K2.7-Code?

LLM.API currently lists: alibaba, canopywave, llmapi-os, novita, togetherai. Availability can vary by region and account.

Where is the canonical page for Kimi K2.7-Code?

https://llmapi.ai/models/moonshotai-kimi-k2-7-code/

Can I use tools or structured outputs with Kimi K2.7-Code?

Tool and/or structured-output flags appear on one or more providers for this model—confirm in the providers table.

How is Kimi K2.7-Code priced on LLM.API?

Listed pricing metadata shows: In $0.74 / 1M tokens · Out $3.5 / 1M tokens. LLM.API may offer discounted effective rates (illustrative ~30% callout vs list when available).. Confirm live rates in the LLM.API dashboard or docs before production budgeting.

When should I choose Kimi K2.7-Code?

Your prompts benefit from the model's family strengths (reasoning, speed, or cost) — especially when you specifically need Kimi K2.7-Code.

Is Kimi K2.7-Code a chat model?

Yes—Kimi K2.7-Code is exposed as a chat/completions-style endpoint on LLM.API.

Which endpoint do I call for Kimi K2.7-Code?

POST https://api.llmapi.ai/v1/chat/completions with model "kimi-k2.7-code" and your LLM.API key. The request and response bodies are OpenAI-compatible.

How do I switch from OpenAI to Kimi K2.7-Code on LLM.API?

Change two lines: set base_url to https://api.llmapi.ai/v1 and api_key to your LLM.API key. The rest of your OpenAI SDK code stays the same.

Does Kimi K2.7-Code support function calling and structured outputs?

Function calling: supported via tools. Structured outputs: supported via response_format. Reasoning effort accepts low, medium, high (default low).

Kimi K2.7-Code: Self-Hosting & Deployment Guide

Call Kimi K2.7-Code through LLM.API when you want Moonshot-family text generation with unified auth, provider choice, and production-friendly defaults.

Start Using API

What is Kimi K2.7-Code?

Kimi K2.7-Code is a Moonshot chat model exposed on LLM.API under id `kimi-k2.7-code`. kimi-k2.7-code provided by moonshot and novita. It is wired for API access through LLM.API with OpenAI-compatible patterns. Teams use it when they need reliable text generation with text, image, video inputs and text outputs over an OpenAI-compatible API.

How to run Kimi K2.7-Code yourself

Open weights (other), 1026.9B parameters. Below: how much memory the weights need at each quantization, which hardware fits them, and the commands to serve it.

Kimi K2.7-Code VRAM requirements

Precision / quantization	Weights	Figure	Source
BF16 (full precision)	2053.8 GB	Estimate	1026.9B params × 2 bytes
MLX 4-bit	643.9 GB	File size	pipenetwork/Kimi-K2.7-Code-MLX-4bit-hiprec

File size = actual download size on Hugging Face. Estimate = parameter count × bytes per weight. Weights only — the KV cache for long contexts needs extra memory; the fit tables below add 15% headroom as a rule of thumb.

GPU requirements: deploy Kimi K2.7-Code on your hardware

Datacenter GPUsApple SiliconCloud instances

Hardware	BF16 (full precision)	MLX 4-bit
NVIDIA H200141 GB	—	6×
NVIDIA H10080 GB	—	—
NVIDIA A100 80GB80 GB	—	—
NVIDIA L40S48 GB	—	—

GPUs needed per variant.

Hardware	MLX 4-bit
Mac, 512 GBM3 Ultra	—
Mac, 192 GBM2 Ultra	—
Mac, 128 GBM4 Max / M3 Max	—
Mac, 64 GBM4 Pro / Max	—

Assumes ~75% of unified memory is usable by the GPU.

Hardware	BF16 (full precision)	MLX 4-bit
AWS p5.48xlarge8× H100 · 640 GB	—	—
AWS p4de.24xlarge8× A100 80GB · 640 GB	—	—
AWS g6e.12xlarge4× L40S · 192 GB	—	—
Google Cloud a3-highgpu-8g8× H100 · 640 GB	—	—
Azure ND H100 v58× H100 · 640 GB	—	—

Whole-instance GPU memory; public instance specs.

Serve it yourself

vLLMSGLangMLX (Mac)

pip install -U vllm
vllm serve moonshotai/Kimi-K2.7-Code

pip install 'sglang[all]'
python -m sglang.launch_server --model-path moonshotai/Kimi-K2.7-Code

pip install -U mlx-lm
mlx_lm.generate --model pipenetwork/Kimi-K2.7-Code-MLX-4bit-hiprec --prompt "Hello"

Commands use the official repositories above; vLLM and SGLang expose an OpenAI-compatible endpoint.

Skip the deploy — use LLM.API as your endpoint

No GPUs, no quantization trade-offs. Same model, OpenAI-compatible, with custom volume discounts on request.

Get API key See API code ↓

Providers

LLM.API routes Kimi K2.7-Code to the providers below, with discounted effective rates versus list price.

List price by provider

InputOutput

llmapi-os$0.74 in

$3.5 out

novita$0.95 in

$4 out

canopywave$0.95 in

$4 out

alibaba$0.95 in

$4 out

Provider list prices; the LLM.API discount applies on top.

Provider	Pricing	Context	Capabilities
llmapi-os	in $0.74; out $3.5 per 1M tokens	262K tokens	vision, tools, streaming, reasoning, JSON, structured
novita	in $0.95; out $4 per 1M tokens	262K tokens	vision, tools, streaming, reasoning, JSON, structured
canopywave	in $0.95; out $4 per 1M tokens	262K tokens	vision, tools, streaming, reasoning, web search, JSON, structured
alibaba	in $0.95; out $4 per 1M tokens	262K tokens	vision, tools, streaming, reasoning, web search, JSON, structured

Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 11 Oct 2026.

Try this model

Test Kimi K2.7-Code right here — free to start.

Kimi K2.7-Code

Hi! Want to test the model?

Suggestions for your first prompt

Code snippet

Call Kimi K2.7-Code through the OpenAI-compatible API — POST /v1/chat/completions.

Switching from OpenAI? Change 2 lines.

- base_url="https://api.openai.com/v1"
- api_key="YOUR_OPENAI_KEY"
+ base_url="https://api.llmapi.ai/v1"
+ api_key="YOUR_LLMAPI_KEY"

Everything else stays the same — SDK, message format, tools, streaming. Set model to kimi-k2.7-code and the call runs unchanged.

bash

curl https://api.llmapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.7-code",
    "messages": [
      {"role": "user", "content": "Give me three crisp launch checklist items."}
    ],
  "reasoning_effort": "low"
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLMAPI_KEY",
    base_url="https://api.llmapi.ai/v1",
)

resp = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[
        {"role": "system", "content": "You are a precise product assistant."},
        {"role": "user", "content": "Give me three crisp launch checklist items."},
    ],
    reasoning_effort="low",
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LLMAPI_KEY,
  baseURL: "https://api.llmapi.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "kimi-k2.7-code",
  messages: [
    { role: "user", content: "Give me three crisp launch checklist items." },
  ],
});

console.log(resp.choices[0].message.content);

stream = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[{"role": "user", "content": "Write a haiku about latency."}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

{
  "model": "kimi-k2.7-code",
  "messages": [
    {"role": "system", "content": "You are a precise product assistant."},
    {"role": "user", "content": "Give me three crisp launch checklist items."}
  ],
  "reasoning_effort": "low"
}

ENDPOINTS

Supported endpoints & features

Base URL https://api.llmapi.ai/v1 · model ID kimi-k2.7-code · OpenAI-compatible.

POST /v1/chat/completionsChat Completions — supported

Feature	Status	How to set it
Function calling (tools)	Supported	`tools, tool_choice`
Parallel tool calls	Not supported	`parallel_tool_calls`
JSON mode	Supported	`response_format: {"type": "json_object"}`
Structured outputs	Supported	`response_format: {"type": "json_schema", …}`
Streaming	Supported	`stream: true`
Vision (image input)	Supported	`image_url content parts`
Web search	Supported	`web_search`
Reasoning effort	low · medium · high	`reasoning_effort: "low"`

ERRORS

Errors & fallback routing

Code	What it means	What to do
`401`	Missing or invalid API key.	Send `Authorization: Bearer YOUR_LLMAPI_KEY` and check the key is active.
`429`	Rate limited, or the upstream provider is throttling the request.	Back off and retry with jitter; the gateway also retries the request on another provider where one is available.
`5xx`	Upstream provider error or timeout.	Retry; fallback routing sends the retry to the next healthy provider for this model.

When a provider fails or throttles, the request is routed to the next provider serving this model — the ones listed in the providers table above.

Kimi K2.7-Code in production

Best workloadsLLM.API features

What the model is good at.

Conversational UX
Maintains coherent multi-turn assistant behavior for product chat surfaces. Grounded in the model's chat role rather than generic chat claims.
Tool-ready dialogue
Works well in agent loops that call functions, browsers, or retrieval APIs.
Structured outputs
Can produce JSON-friendly or schema-oriented responses when prompted carefully. Grounded in the model's chat role rather than generic chat claims.
Analytical writing
Produces clear analyses, comparisons, and decision memos from messy source material. Reflects Moonshot positioning for this endpoint.
Code assistance
Helps write, explain, refactor, and debug application code across common languages.

What you get when you call Kimi K2.7-Code through LLM.API.

Unified AI Routing
Production: Reach Kimi K2.7-Code and sibling models through one OpenAI-compatible endpoint.
One endpoint, every model.
Cost Control
Practical: Compare provider price points and keep spend visible as you scale Kimi K2.7-Code.
More performance, less spend.
Reliability Layer
Practical: Retry and route across configured providers when a single upstream blips.
Never go dark on users.
Observability
Trace prompts, tokens, and errors for Kimi K2.7-Code alongside the rest of your stack.
See every token, everywhere.
Drop-in SDKs
Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.
Think tasks, not models.
Model Breadth
Swap Kimi K2.7-Code for chat, media, or embedding alternatives without rewriting auth.
Scale from 1 to millions.

When to Use — When NOT to Use

Use it if...

You need provider failover options exposed for this model id (Kimi K2.7-Code)
Your prompts benefit from the model's family strengths (reasoning, speed, or cost) (Kimi K2.7-Code)
You need a general-purpose text model for assistants, agents, or content workflows (Kimi K2.7-Code)
You want OpenAI-compatible chat completions through a single LLM.API key (Kimi K2.7-Code)

Avoid if...

You need pure embedding, OCR, or media generation instead of chat
Your use case depends on unpublished proprietary benchmarks not listed here
You require on-prem only deployment with no cloud inference
You need guaranteed real-time hard latency SLAs without benchmarking the provider

LLM API rating for Kimi K2.7-Code

★ 3.2/ 5.0LLM API rating
50% production adoption · 30% category benchmark · 20% tooling & value✓ Verified benchmark · Artificial Analysis

3.5Production adoptionActive open-weight community usage

2.7Benchmark qualityArtificial Analysis Intelligence Index 25.8

3.4Developer ecosystemContext window, tool and JSON support, price against the category median

Reasoning & chat 3.2Coding 3.2Vision & multimodal 3.4Tool & function calling 3.8Long context 3.6

How is this rating calculated?

Every model gets a separate 1.0–5.0 score for each category it can be used in, so a model can rate high for coding and lower for vision. The score combines three parts:

Production adoption — 50%. How widely the model is actually used in production: provider traffic, LiteLLM and gateway usage, open-weight downloads and its LMArena rank. Proven, widely used models score highest.
Category benchmark — 30%. The public benchmark that matters for that category — the Artificial Analysis Intelligence Index and LMArena Elo for reasoning, LMArena coding Elo for coding, image and document support plus vision Elo for vision, tool and JSON support for function calling, measured speed for voice.
Tooling & value — 20%. Context window, support for tools, structured outputs and streaming, and price compared with the category median.

Scores of 4.0 and above are shown in green, 3.0–3.9 in yellow, below 3.0 in red. When a model has no public data for a part, it gets a neutral value instead of an invented number.

A “Verified benchmark” mark (✓) means an independent lab — LMArena or Artificial Analysis — has actually tested that model, and the source figure is shown. Models without that mark are labelled “Estimated from published specs”: the score comes from the published context window, tool and schema support, price and adoption only, because no independent lab has tested them yet.

One exception: a brand-new top-tier model that scores very high on the independent benchmarks but has no usage history yet is rated on the benchmark (60%) and tooling & value (40%) alone, so a missing adoption figure can't hold it back. All inputs come from public sources and are refreshed weekly.

Adoption and benchmark inputs come from public sources — LMArena, Artificial Analysis Intelligence Index and published model specs. Updated weekly.

BENCHMARKS

Kimi K2.7-Code benchmark scores

Intelligence index

This model26.

Tracked median18.

Scale: 0-100 index points

Output speed

This model50 t/s

Scale: 0-400 tokens per second

Reference price per 1M tokens

Input$0.95

Output$4.00

Bars compare input and output list prices for this model.

Intelligence index+44% vs median

Kimi K2.7-Code: Self-Hosting & Deployment Guide26

Median tracked model18

Higher is better. The median covers every model tracked by Artificial Analysis.

Output speed

50tok/s

Measured throughput; the full dial is 300 tokens per second.

Reference price / 1M tokens

Input$0.95

Output$4.00

Provider list prices, before the LLM.API discount.

Independent scores published by Artificial Analysis (source). Reference prices are provider list prices, not LLM.API pricing.

COMMUNITY

What developers say about Kimi models

LMArena—Speed50 tokens/sSources: LMArena, Artificial Analysis

Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to Kimi K2.7-Code.

30-day hands-on reviews describe Kimi K2 as a capable, affordable alternative for coding and agent work.
Community round-ups praise the generous free tier and long context, with speed under load the most common complaint.
Developers commonly use it as a second opinion model alongside a frontier assistant.

SOURCES

Frequently Asked Questions

Does Kimi K2.7-Code support streaming?
Yes—at least one listed provider advertises streaming.
What are limitations of Kimi K2.7-Code?
Like other API models, Kimi K2.7-Code can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
What is Kimi K2.7-Code?
kimi-k2.7-code provided by moonshot and novita. It is wired for API access through LLM.API with OpenAI-compatible patterns. On LLM.API it is addressed as `kimi-k2.7-code`.
What modalities does Kimi K2.7-Code support?
Kimi K2.7-Code accepts text, image, video and produces text according to its architecture metadata on LLM.API.
How do I call Kimi K2.7-Code via API?
Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "kimi-k2.7-code" and your LLM.API key. See the code snippet on this page.
Which providers serve Kimi K2.7-Code?
LLM.API currently lists: alibaba, canopywave, llmapi-os, novita, togetherai. Availability can vary by region and account.
Where is the canonical page for Kimi K2.7-Code?
https://llmapi.ai/models/moonshotai-kimi-k2-7-code/
Can I use tools or structured outputs with Kimi K2.7-Code?
Tool and/or structured-output flags appear on one or more providers for this model—confirm in the providers table.
How is Kimi K2.7-Code priced on LLM.API?
Listed pricing metadata shows: In $0.74 / 1M tokens · Out $3.5 / 1M tokens. LLM.API may offer discounted effective rates (illustrative ~30% callout vs list when available).. Confirm live rates in the LLM.API dashboard or docs before production budgeting.
When should I choose Kimi K2.7-Code?
Your prompts benefit from the model's family strengths (reasoning, speed, or cost) — especially when you specifically need Kimi K2.7-Code.
Is Kimi K2.7-Code a chat model?
Yes—Kimi K2.7-Code is exposed as a chat/completions-style endpoint on LLM.API.

COMPARE

Competitive Models

Get one key to every model

Swap your API key. Keep your code.

Start for free Talk to sales

LLM API sells to AI agents - live prices and self-serve payment

Kimi K2.7-Code: Self-Hosting & Deployment Guide

What is Kimi K2.7-Code?

How to run Kimi K2.7-Code yourself

Kimi K2.7-Code VRAM requirements

GPU requirements: deploy Kimi K2.7-Code on your hardware

Serve it yourself

Providers

Try this model

Code snippet

Supported endpoints & features

Errors & fallback routing

Kimi K2.7-Code in production

Conversational UX

Tool-ready dialogue

Structured outputs

Analytical writing

Code assistance

Unified AI Routing

Cost Control

Reliability Layer

Observability

Drop-in SDKs

Model Breadth

When to Use — When NOT to Use

Use it if...

Avoid if...

LLM API rating for Kimi K2.7-Code

Kimi K2.7-Code benchmark scores

Intelligence index

Output speed

Reference price per 1M tokens

What developers say about Kimi models

Frequently Asked Questions

Competitive Models

Kimi K2.6

Qwen3 Max

GPT-5.4 Mini

Get one key to every model