Model detail
Kimi K2.8 Preview
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/completionsPOST
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
Tool calling
kimi-k2.8-preview supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Streaming
kimi-k2.8-preview supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
kimi-k2.8-preview supports prompt caching under supported routing conditions.
Vision input
kimi-k2.8-preview can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call kimi-k2.8-preview through MixRoute's OpenAI-compatible endpoint.
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.
More from Moonshot
All Moonshot modelsOne 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.