Skip to content

Model detail

Kimi K2.8 Preview

Provided by Moonshot
Pay-as-you-go

Kimi K2.8 Preview is Moonshot's coding and agent preview model, served through the rolling kimi-for-coding identifier. It accepts text, images, and video and returns text for development workflows.

Model specs

Model ID
kimi-k2.8-preview
Context length
1.048576M
Max output
–
I/O modalities
Released
2026-09

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Pricing updated

Input

$75.0000 /1M Tokens

Completion

$75.0000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Coding

Kimi K2.8 Preview is built for writing and reviewing code, and it reads images alongside text. It accepts text, image and video input and returns text. Its capabilities are broken down in the section just below. Run it on one file from your own repository and check the patch before you commit.

What should you check before using it?

1,048,576 context tokens

Kimi K2.8 Preview accepts up to 1,048,576 tokens of context per request. Check that your longest prompt and its expected answer fit inside both limits before you size production traffic.

Why use it through MixRoute?

Swap the base URL, keep the Kimi K2.8 Preview client

Keep your existing OpenAI client and swap only the base URL. MixRoute supports calling Kimi K2.8 Preview through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID kimi-k2.8-preview and re-run your integration tests.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Tool calling

kimi-k2.8-preview supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.
Available:

Streaming

kimi-k2.8-preview supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.
Available:

Prompt caching

kimi-k2.8-preview supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.
Available:

Vision input

kimi-k2.8-preview can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.
Available:

OpenAI SDK

Call kimi-k2.8-preview through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

This model has no cache-read price; caching is not counted

09

FAQ

Before switching production traffic to kimi-k2.8-preview, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.