kimi-for-coding

by Moonshot AIChat

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

Context: 1.05M tokens
Max output: 32,768 tokens
Released: 2026-09-11
Weights: Closed

Feed

moonshotai/kimi-k2-8-preview · also seen as kimi-for-coding

Specifications

Full facts as recorded, incl. what is unknown.

Released: 2026-09-11
Weights: Closed
Input: Text, Image, Video
Output: Text
Context window: 1,048,576 max across endpoints
Max output: 32,768
Providers: 3
Epoch Capabilities Index: not evaluated
Direct price range: $1.00 in · $4.00 out per 1M tokens · 1 of 3 providers have a comparable price

More details

Last updated: 2026-09-11
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

Tool calling
Parallel toolsunknown
Structured output
Reasoning
Image input
PDF input
Audio input
Audio outputunknown
Video input
Prompt caching
Web searchunknown
Computer useunknown
System messages
Assistant prefillunknown
Temperatureunknown
Streaming
Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

Atom feed

No change since 19 Oct 2026. The cheapest direct price has been $1.00 in / $4.00 out per 1M tokens at Tencent on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

More from Moonshot AI

Newest Moonshot AI models in the catalogue. All Moonshot AI models

Model	Released	Context	Listed price
Kimi K3	2026-07-16	1.05M	from $1.85
Kimi K2.7 Code HighSpeed	2026-06-12	262K	from $0.66
Kimi Latest	2026-05-03	1.05M	$1.65 via NanoGPT
Kimi K2.6	2026-04-21	262K	from $0.45
Kimi-K2.5-FW	2026-01-27	262K	unpriced
Kimi K2.5 Free	2026-01-27	262K	unpriced
Moonshot Kimi K2.5	2026-01	262K	from $0.45
Kimi K2 0711 Fast	2025-12-15	131K	$0.40 via NanoGPT

Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model